diff --git a/docs/source/manual/arch_lang/annotate_vpr_arch.rst b/docs/source/manual/arch_lang/annotate_vpr_arch.rst
index a23b4f0c6..9fd1024a7 100644
--- a/docs/source/manual/arch_lang/annotate_vpr_arch.rst
+++ b/docs/source/manual/arch_lang/annotate_vpr_arch.rst
@@ -62,12 +62,37 @@ Here is an example:
 .. code-block:: xml
 
   <tile_annotations>
+    <merge_subtile_ports tile="<string>" port="<string>"/>
     <global_port name="<string>" is_clock="<bool>" clock_arch_tree_name="<string>" is_reset="<bool>" is_set="<bool>" default_val="<int>">
       <tile name="<string>" port="<string>" x="<int>" y="<int>"/>
       ...
     </global_port>
   </tile_annotations>
 
+For subtile port merge support (see an illustrative example in :numref:`fig_subtile_port_merge`):
+
+- ``tile="<string>"`` is the name of tile, that is defined in VPR architecture
+
+- ``port="<string>"`` is the name of a port of the tile, that is defined in VPR architecture
+
+.. warning:: This is an option for power users. Suggest to enable for those global input ports, such as clock and reset, whose ``Fc`` is set to 0 in VPR architecture!!!
+
+.. note:: When defined, the given port of all the subtiles of a tile will be merged into one port. For example, a tile consists of 8 subtile ``A`` and 6 subtile ``B`` and all the subtiles have a port ``clk``, in the FPGA fabric, all the ``clk`` of the subtiles ``A`` and ``B`` will be wired to a common port ``clk`` at tile level.
+
+
+.. note:: When merged, the port will have a default side of ``TOP`` and index of ``0`` on all the attributes, such as width, height etc.
+
+.. _fig_subtile_port_merge:
+
+.. figure:: ./figures/subtile_port_merge.png
+   :width: 100%
+   :alt: Difference in netlists with and without subtile port merging
+
+   Difference in netlists with and without subtile port merging
+
+
+For global port support:
+
 - ``name="<string>"`` is the port name to appear in the top-level FPGA fabric.
 
 - ``is_clock="<bool>"`` define if the global port is a clock port at the top-level FPGA fabric. An operating clock port will be driven by proper signals in auto-generated testbenches.
@@ -111,7 +136,7 @@ A more illustrative example:
 .. _fig_global_tile_ports:
 
 .. figure:: ./figures/global_tile_ports.png
-   :scale: 100%
+   :width: 100%
    :alt: Difference between global port definition through circuit model and tile annotation
 
    Difference between global port definition through circuit model and tile annotation
diff --git a/docs/source/manual/arch_lang/figures/subtile_port_merge.png b/docs/source/manual/arch_lang/figures/subtile_port_merge.png
new file mode 100644
index 000000000..16f7c6021
Binary files /dev/null and b/docs/source/manual/arch_lang/figures/subtile_port_merge.png differ
diff --git a/libs/libarchopenfpga/CMakeLists.txt b/libs/libarchopenfpga/CMakeLists.txt
index 93c20710d..13b4431f1 100644
--- a/libs/libarchopenfpga/CMakeLists.txt
+++ b/libs/libarchopenfpga/CMakeLists.txt
@@ -20,6 +20,7 @@ set_target_properties(libarchopenfpga PROPERTIES PREFIX "") #Avoid extra 'lib' p
 #Specify link-time dependancies
 target_link_libraries(libarchopenfpga
                       libopenfpgautil
+                      libopenfpgashell
                       libvtrutil
                       libarchfpga
                       libpugiutil)
diff --git a/libs/libarchopenfpga/src/read_xml_tile_annotation.cpp b/libs/libarchopenfpga/src/read_xml_tile_annotation.cpp
index 6b27d0017..135e38361 100644
--- a/libs/libarchopenfpga/src/read_xml_tile_annotation.cpp
+++ b/libs/libarchopenfpga/src/read_xml_tile_annotation.cpp
@@ -125,6 +125,22 @@ static void read_xml_tile_global_port_annotation(
   }
 }
 
+/********************************************************************
+ * Parse XML description for an interconnection annotation
+ * under a <global_port> XML node
+ *******************************************************************/
+static void read_xml_tile_merge_port_annotation(
+  pugi::xml_node& xml_tile, const pugiutil::loc_data& loc_data,
+  openfpga::TileAnnotation& tile_annotation) {
+  const std::string& tile_attr =
+    get_attribute(xml_tile, "tile", loc_data).as_string();
+
+  const std::string& port_attr =
+    get_attribute(xml_tile, "port", loc_data).as_string();
+
+  tile_annotation.add_merge_subtile_ports(tile_attr, port_attr);
+}
+
 /********************************************************************
  * Top function to parse XML description about tile annotation
  *******************************************************************/
@@ -146,11 +162,17 @@ openfpga::TileAnnotation read_xml_tile_annotations(
    */
   for (pugi::xml_node xml_tile_global_port : xml_annotations.children()) {
     /* Error out if the XML child has an invalid name! */
-    if (xml_tile_global_port.name() != std::string("global_port")) {
-      bad_tag(xml_tile_global_port, loc_data, xml_annotations, {"global_port"});
+    if (xml_tile_global_port.name() == std::string("global_port")) {
+      read_xml_tile_global_port_annotation(xml_tile_global_port, loc_data,
+                                           tile_annotations);
+    } else if (xml_tile_global_port.name() ==
+               std::string("merge_subtile_ports")) {
+      read_xml_tile_merge_port_annotation(xml_tile_global_port, loc_data,
+                                          tile_annotations);
+    } else {
+      bad_tag(xml_tile_global_port, loc_data, xml_annotations,
+              {"global_port or merge_subtile_ports"});
     }
-    read_xml_tile_global_port_annotation(xml_tile_global_port, loc_data,
-                                         tile_annotations);
   }
 
   return tile_annotations;
diff --git a/libs/libarchopenfpga/src/tile_annotation.cpp b/libs/libarchopenfpga/src/tile_annotation.cpp
index 7cf41f02e..2ffacd1d0 100644
--- a/libs/libarchopenfpga/src/tile_annotation.cpp
+++ b/libs/libarchopenfpga/src/tile_annotation.cpp
@@ -3,7 +3,11 @@
  ***********************************************************************/
 #include "tile_annotation.h"
 
+#include <algorithm>
+
+#include "command_exit_codes.h"
 #include "vtr_assert.h"
+#include "vtr_log.h"
 
 /* namespace openfpga begins */
 namespace openfpga {
@@ -20,6 +24,27 @@ TileAnnotation::global_port_range TileAnnotation::global_ports() const {
   return vtr::make_range(global_port_ids_.begin(), global_port_ids_.end());
 }
 
+std::vector<std::string> TileAnnotation::tiles_to_merge_ports() const {
+  std::vector<std::string> tile_names;
+  for (auto it = tile_ports_to_merge_.begin(); it != tile_ports_to_merge_.end();
+       it++) {
+    tile_names.push_back(it->first);
+  }
+  return tile_names;
+}
+
+std::vector<std::string> TileAnnotation::tile_ports_to_merge(
+  const std::string& tile_name) const {
+  std::vector<std::string> port_names;
+  const auto& result = tile_ports_to_merge_.find(tile_name);
+  if (result == tile_ports_to_merge_.end()) {
+    VTR_LOG_WARN("Tile '%s' does not contain any ports to merge!\n",
+                 tile_name.c_str());
+    return port_names;
+  }
+  return result->second;
+}
+
 /************************************************************************
  * Public Accessors
  ***********************************************************************/
@@ -77,6 +102,16 @@ std::string TileAnnotation::global_port_clock_arch_tree_name(
   return global_port_clock_arch_tree_names_[global_port_id];
 }
 
+bool TileAnnotation::is_tile_port_to_merge(const std::string& tile_name,
+                                           const std::string& port_name) const {
+  const auto& result = tile_ports_to_merge_.find(tile_name);
+  if (result == tile_ports_to_merge_.end()) {
+    return false;
+  }
+  return result->second.end() !=
+         std::find(result->second.begin(), result->second.end(), port_name);
+}
+
 /************************************************************************
  * Public Mutators
  ***********************************************************************/
@@ -178,4 +213,25 @@ bool TileAnnotation::valid_global_port_attributes(
   return ((0 == attribute_counter) || (1 == attribute_counter));
 }
 
+int TileAnnotation::add_merge_subtile_ports(const std::string& tile_name,
+                                            const std::string& port_name) {
+  auto result = tile_ports_to_merge_.find(tile_name);
+  if (result == tile_ports_to_merge_.end()) {
+    /* Empty list: add a new element */
+    tile_ports_to_merge_[tile_name].push_back(port_name);
+  } else {
+    /* Check if the port name is already in the list, if yes, error out */
+    if (result->second.end() ==
+        std::find(result->second.begin(), result->second.end(), port_name)) {
+      tile_ports_to_merge_[tile_name].push_back(port_name);
+    } else {
+      VTR_LOG_ERROR(
+        "Port '%s' has already been defined twice for tile '%s' to be merged!",
+        port_name.c_str(), tile_name.c_str());
+      return CMD_EXEC_FATAL_ERROR;
+    }
+  }
+  return CMD_EXEC_SUCCESS;
+}
+
 }  // namespace openfpga
diff --git a/libs/libarchopenfpga/src/tile_annotation.h b/libs/libarchopenfpga/src/tile_annotation.h
index ddf951109..36af8a9b4 100644
--- a/libs/libarchopenfpga/src/tile_annotation.h
+++ b/libs/libarchopenfpga/src/tile_annotation.h
@@ -39,6 +39,9 @@ class TileAnnotation {
 
  public: /* Public accessors: aggregators */
   global_port_range global_ports() const;
+  std::vector<std::string> tiles_to_merge_ports() const;
+  std::vector<std::string> tile_ports_to_merge(
+    const std::string& tile_name) const;
 
  public: /* Public accessors */
   std::string global_port_name(const TileGlobalPortId& global_port_id) const;
@@ -56,6 +59,10 @@ class TileAnnotation {
   size_t global_port_default_value(
     const TileGlobalPortId& global_port_id) const;
 
+  /** @brief Check if a given tile port should be merged or not */
+  bool is_tile_port_to_merge(const std::string& tile_name,
+                             const std::string& port_name) const;
+
  public: /* Public mutators */
   /* By default, we do not set it as a clock.
    * Users should set it through the set_global_port_is_clock() function
@@ -77,6 +84,9 @@ class TileAnnotation {
   void set_global_port_default_value(const TileGlobalPortId& global_port_id,
                                      const size_t& default_value);
 
+  int add_merge_subtile_ports(const std::string& tile_name,
+                              const std::string& port_name);
+
  public: /* Public validator */
   bool valid_global_port_id(const TileGlobalPortId& global_port_id) const;
   /* Validate attributes of a given global port
@@ -102,6 +112,10 @@ class TileAnnotation {
 
   /* A fast lookup for port names */
   std::map<std::string, TileGlobalPortId> global_port_name2ids_;
+
+  /* Merge port information for tiles */
+  std::map<std::string, std::vector<std::string>>
+    tile_ports_to_merge_;  // tile_name -> port_name
 };
 
 }  // namespace openfpga
diff --git a/libs/libarchopenfpga/src/write_xml_tile_annotation.cpp b/libs/libarchopenfpga/src/write_xml_tile_annotation.cpp
index af6bab25a..9db2e01b7 100644
--- a/libs/libarchopenfpga/src/write_xml_tile_annotation.cpp
+++ b/libs/libarchopenfpga/src/write_xml_tile_annotation.cpp
@@ -87,6 +87,24 @@ static void write_xml_tile_annotation_global_port(
      << "</global_port>";
 }
 
+/********************************************************************
+ * A writer to output a device variation in a technology library to XML format
+ *******************************************************************/
+static void write_xml_tile_annotation_subtile_port_to_merge(
+  std::fstream& fp, const char* fname, const std::string& tile_name,
+  const std::string& port_name) {
+  /* Validate the file stream */
+  openfpga::check_file_stream(fname, fp);
+
+  fp << "\t\t"
+     << "<merge_subtile_ports ";
+
+  write_xml_attribute(fp, "tile", tile_name.c_str());
+  write_xml_attribute(fp, "port", port_name.c_str());
+
+  fp << "/>";
+}
+
 /********************************************************************
  * A writer to output tile annotations to XML format
  *******************************************************************/
@@ -109,6 +127,13 @@ void write_xml_tile_annotations(std::fstream& fp, const char* fname,
     write_xml_tile_annotation_global_port(fp, fname, tile_annotation,
                                           global_port_id);
   }
+  for (std::string tile_name : tile_annotation.tiles_to_merge_ports()) {
+    for (std::string port_name :
+         tile_annotation.tile_ports_to_merge(tile_name)) {
+      write_xml_tile_annotation_subtile_port_to_merge(fp, fname, tile_name,
+                                                      port_name);
+    }
+  }
 
   /* Write the root node for pb_type annotations */
   fp << "\t"
diff --git a/libs/libnamemanager/test/module_rename_assistant.cpp b/libs/libnamemanager/test/module_rename_assistant.cpp
index a4e662f02..49de367c3 100644
--- a/libs/libnamemanager/test/module_rename_assistant.cpp
+++ b/libs/libnamemanager/test/module_rename_assistant.cpp
@@ -36,7 +36,7 @@ static std::vector<std::string> format_argv(const std::string& cmd_name,
  * We want a renamed version for fabric B is
  *   <module_name default="tile_2__2_" given="tile_big"/>
  */
-int rename_module_names_for_fabricB_from_fabricA(
+static int rename_module_names_for_fabricB_from_fabricA(
   const openfpga::ModuleNameMap& refA_module_names,
   const openfpga::ModuleNameMap& renamedA_module_names,
   const openfpga::ModuleNameMap& refB_module_names,
diff --git a/openfpga/src/base/openfpga_build_fabric_template.h b/openfpga/src/base/openfpga_build_fabric_template.h
index d3d94c3e7..63e623398 100644
--- a/openfpga/src/base/openfpga_build_fabric_template.h
+++ b/openfpga/src/base/openfpga_build_fabric_template.h
@@ -130,6 +130,16 @@ int build_fabric_template(T& openfpga_ctx, const Command& cmd,
       return CMD_EXEC_FATAL_ERROR;
     }
   }
+  /* Conflicts: duplicate_grid_pin does not support any port merge */
+  if (cmd_context.option_enable(cmd, opt_duplicate_grid_pin)) {
+    if (openfpga_ctx.arch().tile_annotations.tiles_to_merge_ports().size() >
+        0) {
+      VTR_LOG_ERROR(
+        "Option '%s' requires no tile ports to be merged due to a conflict!\n",
+        cmd.option_name(opt_duplicate_grid_pin).c_str());
+      return CMD_EXEC_FATAL_ERROR;
+    }
+  }
 
   if (true == cmd_context.option_enable(cmd, opt_compress_routing)) {
     compress_routing_hierarchy_template<T>(
diff --git a/openfpga/src/fabric/build_device_module.cpp b/openfpga/src/fabric/build_device_module.cpp
index 8a4b176d7..012e3a529 100644
--- a/openfpga/src/fabric/build_device_module.cpp
+++ b/openfpga/src/fabric/build_device_module.cpp
@@ -87,8 +87,9 @@ int build_device_module_graph(
   status = build_grid_modules(
     module_manager, decoder_lib, vpr_device_ctx,
     openfpga_ctx.vpr_device_annotation(), openfpga_ctx.arch().circuit_lib,
-    openfpga_ctx.mux_lib(), openfpga_ctx.arch().config_protocol.type(),
-    sram_model, duplicate_grid_pin, group_config_block, verbose);
+    openfpga_ctx.mux_lib(), openfpga_ctx.arch().tile_annotations,
+    openfpga_ctx.arch().config_protocol.type(), sram_model, duplicate_grid_pin,
+    group_config_block, verbose);
   if (CMD_EXEC_FATAL_ERROR == status) {
     return status;
   }
@@ -120,13 +121,13 @@ int build_device_module_graph(
       return status;
     }
     /* Build the modules */
-    build_tile_modules(module_manager, decoder_lib, openfpga_ctx.fabric_tile(),
-                       vpr_device_ctx.grid,
-                       openfpga_ctx.vpr_device_annotation(),
-                       openfpga_ctx.device_rr_gsb(), vpr_device_ctx.rr_graph,
-                       openfpga_ctx.arch().circuit_lib, sram_model,
-                       openfpga_ctx.arch().config_protocol.type(),
-                       name_module_using_index, frame_view, verbose);
+    build_tile_modules(
+      module_manager, decoder_lib, openfpga_ctx.fabric_tile(),
+      vpr_device_ctx.grid, openfpga_ctx.vpr_device_annotation(),
+      openfpga_ctx.device_rr_gsb(), vpr_device_ctx.rr_graph,
+      openfpga_ctx.arch().tile_annotations, openfpga_ctx.arch().circuit_lib,
+      sram_model, openfpga_ctx.arch().config_protocol.type(),
+      name_module_using_index, frame_view, verbose);
   }
 
   /* Build FPGA fabric top-level module */
diff --git a/openfpga/src/fabric/build_grid_module_duplicated_pins.cpp b/openfpga/src/fabric/build_grid_module_duplicated_pins.cpp
index 77f4024db..cae215259 100644
--- a/openfpga/src/fabric/build_grid_module_duplicated_pins.cpp
+++ b/openfpga/src/fabric/build_grid_module_duplicated_pins.cpp
@@ -54,7 +54,8 @@ namespace openfpga {
 void add_grid_module_duplicated_pb_type_ports(
   ModuleManager& module_manager, const ModuleId& grid_module,
   const VprDeviceAnnotation& vpr_device_annotation,
-  t_physical_tile_type_ptr grid_type_descriptor, const e_side& border_side) {
+  t_physical_tile_type_ptr grid_type_descriptor,
+  const TileAnnotation& tile_annotation, const e_side& border_side) {
   /* Ensure that we have a valid grid_type_descriptor */
   VTR_ASSERT(false == is_empty_type(grid_type_descriptor));
 
@@ -109,6 +110,17 @@ void add_grid_module_duplicated_pb_type_ports(
                (0. == find_physical_tile_pin_Fc(grid_type_descriptor, ipin)))) {
             std::string port_name = generate_grid_port_name(
               iwidth, iheight, subtile_index, side, pin_info);
+            /* If the port is required to be merged, we deposit zero as subtile
+             * index */
+            if (tile_annotation.is_tile_port_to_merge(
+                  std::string(grid_type_descriptor->name),
+                  pin_info.get_name())) {
+              if (subtile_index == 0) {
+                port_name = generate_grid_port_name(0, 0, 0, TOP, pin_info);
+              } else {
+                continue;
+              }
+            }
             BasicPort grid_port(port_name, 0, 0);
             /* Add the port to the module */
             module_manager.add_port(grid_module, grid_port,
@@ -297,7 +309,8 @@ void add_grid_module_nets_connect_duplicated_pb_type_ports(
   ModuleManager& module_manager, const ModuleId& grid_module,
   const ModuleId& child_module, const size_t& child_instance,
   const t_sub_tile& sub_tile, const VprDeviceAnnotation& vpr_device_annotation,
-  t_physical_tile_type_ptr grid_type_descriptor, const e_side& border_side) {
+  t_physical_tile_type_ptr grid_type_descriptor,
+  const TileAnnotation& tile_annotation, const e_side& border_side) {
   /* Ensure that we have a valid grid_type_descriptor */
   VTR_ASSERT(false == is_empty_type(grid_type_descriptor));
 
@@ -314,8 +327,8 @@ void add_grid_module_nets_connect_duplicated_pb_type_ports(
       add_grid_module_net_connect_pb_graph_pin(
         module_manager, grid_module, child_module, child_instance,
         child_inst_subtile_index, vpr_device_annotation, grid_type_descriptor,
-        &(top_pb_graph_node->input_pins[iport][ipin]), border_side,
-        INPUT2INPUT_INTERC);
+        tile_annotation, &(top_pb_graph_node->input_pins[iport][ipin]),
+        border_side, INPUT2INPUT_INTERC);
     }
   }
 
@@ -336,8 +349,8 @@ void add_grid_module_nets_connect_duplicated_pb_type_ports(
       add_grid_module_net_connect_pb_graph_pin(
         module_manager, grid_module, child_module, child_instance,
         child_inst_subtile_index, vpr_device_annotation, grid_type_descriptor,
-        &(top_pb_graph_node->clock_pins[iport][ipin]), border_side,
-        INPUT2INPUT_INTERC);
+        tile_annotation, &(top_pb_graph_node->clock_pins[iport][ipin]),
+        border_side, INPUT2INPUT_INTERC);
     }
   }
 }
diff --git a/openfpga/src/fabric/build_grid_module_duplicated_pins.h b/openfpga/src/fabric/build_grid_module_duplicated_pins.h
index 66e1a5634..4f2eafee2 100644
--- a/openfpga/src/fabric/build_grid_module_duplicated_pins.h
+++ b/openfpga/src/fabric/build_grid_module_duplicated_pins.h
@@ -7,6 +7,7 @@
 #include "module_manager.h"
 #include "openfpga_side_manager.h"
 #include "physical_types.h"
+#include "tile_annotation.h"
 #include "vpr_device_annotation.h"
 
 /********************************************************************
@@ -19,13 +20,15 @@ namespace openfpga {
 void add_grid_module_duplicated_pb_type_ports(
   ModuleManager& module_manager, const ModuleId& grid_module,
   const VprDeviceAnnotation& vpr_device_annotation,
-  t_physical_tile_type_ptr grid_type_descriptor, const e_side& border_side);
+  t_physical_tile_type_ptr grid_type_descriptor,
+  const TileAnnotation& tile_annotation, const e_side& border_side);
 
 void add_grid_module_nets_connect_duplicated_pb_type_ports(
   ModuleManager& module_manager, const ModuleId& grid_module,
   const ModuleId& child_module, const size_t& child_instance,
   const t_sub_tile& sub_tile, const VprDeviceAnnotation& vpr_device_annotation,
-  t_physical_tile_type_ptr grid_type_descriptor, const e_side& border_side);
+  t_physical_tile_type_ptr grid_type_descriptor,
+  const TileAnnotation& tile_annotation, const e_side& border_side);
 
 } /* end namespace openfpga */
 
diff --git a/openfpga/src/fabric/build_grid_module_utils.cpp b/openfpga/src/fabric/build_grid_module_utils.cpp
index c79262805..3b3f14203 100644
--- a/openfpga/src/fabric/build_grid_module_utils.cpp
+++ b/openfpga/src/fabric/build_grid_module_utils.cpp
@@ -45,7 +45,8 @@ void add_grid_module_net_connect_pb_graph_pin(
   const ModuleId& child_module, const size_t& child_instance,
   const size_t& child_inst_subtile_index,
   const VprDeviceAnnotation& vpr_device_annotation,
-  t_physical_tile_type_ptr grid_type_descriptor, t_pb_graph_pin* pb_graph_pin,
+  t_physical_tile_type_ptr grid_type_descriptor,
+  const TileAnnotation& tile_annotation, t_pb_graph_pin* pb_graph_pin,
   const e_side& border_side, const e_pin2pin_interc_type& pin2pin_interc_type) {
   /* Find the pin side for I/O grids*/
   std::vector<e_side> grid_pin_sides;
@@ -91,6 +92,13 @@ void add_grid_module_net_connect_pb_graph_pin(
                subtile_index < grid_type_descriptor->capacity);
     std::string grid_port_name = generate_grid_port_name(
       pin_width, pin_height, subtile_index, side, pin_info);
+    /* If the port is required to be merged, we only consider the source port to
+     * be the subtile index of 0 */
+    if (tile_annotation.is_tile_port_to_merge(
+          std::string(grid_type_descriptor->name), pin_info.get_name())) {
+      /* Exception: use top side for these merged ports */
+      grid_port_name = generate_grid_port_name(0, 0, 0, TOP, pin_info);
+    }
     ModulePortId grid_module_port_id =
       module_manager.find_module_port(grid_module, grid_port_name);
     VTR_ASSERT(true == module_manager.valid_module_port_id(
diff --git a/openfpga/src/fabric/build_grid_module_utils.h b/openfpga/src/fabric/build_grid_module_utils.h
index c1f0549dd..a8d5f9d12 100644
--- a/openfpga/src/fabric/build_grid_module_utils.h
+++ b/openfpga/src/fabric/build_grid_module_utils.h
@@ -8,6 +8,7 @@
 #include "module_manager.h"
 #include "openfpga_interconnect_types.h"
 #include "physical_types.h"
+#include "tile_annotation.h"
 #include "vpr_device_annotation.h"
 
 /********************************************************************
@@ -25,7 +26,8 @@ void add_grid_module_net_connect_pb_graph_pin(
   const ModuleId& child_module, const size_t& child_instance,
   const size_t& child_inst_subtile_index,
   const VprDeviceAnnotation& vpr_device_annotation,
-  t_physical_tile_type_ptr grid_type_descriptor, t_pb_graph_pin* pb_graph_pin,
+  t_physical_tile_type_ptr grid_type_descriptor,
+  const TileAnnotation& tile_annotation, t_pb_graph_pin* pb_graph_pin,
   const e_side& border_side,
   const enum e_pin2pin_interc_type& pin2pin_interc_type);
 
diff --git a/openfpga/src/fabric/build_grid_modules.cpp b/openfpga/src/fabric/build_grid_modules.cpp
index bf8ca86ac..ad49cc63c 100644
--- a/openfpga/src/fabric/build_grid_modules.cpp
+++ b/openfpga/src/fabric/build_grid_modules.cpp
@@ -41,7 +41,8 @@ namespace openfpga {
 static void add_grid_module_pb_type_ports(
   ModuleManager& module_manager, const ModuleId& grid_module,
   const VprDeviceAnnotation& vpr_device_annotation,
-  t_physical_tile_type_ptr grid_type_descriptor, const e_side& border_side) {
+  t_physical_tile_type_ptr grid_type_descriptor,
+  const TileAnnotation& tile_annotation, const e_side& border_side) {
   /* Ensure that we have a valid grid_type_descriptor */
   VTR_ASSERT(nullptr != grid_type_descriptor);
 
@@ -90,6 +91,16 @@ static void add_grid_module_pb_type_ports(
                      subtile_index < grid_type_descriptor->capacity);
           std::string port_name = generate_grid_port_name(
             iwidth, iheight, subtile_index, side, pin_info);
+          /* If the port is required to be merged, we use a special index
+           * index */
+          if (tile_annotation.is_tile_port_to_merge(
+                std::string(grid_type_descriptor->name), pin_info.get_name())) {
+            if (subtile_index == 0) {
+              port_name = generate_grid_port_name(0, 0, 0, TOP, pin_info);
+            } else {
+              continue;
+            }
+          }
           BasicPort grid_port(port_name, 0, 0);
           /* Add the port to the module */
           module_manager.add_port(grid_module, grid_port,
@@ -111,7 +122,8 @@ static void add_grid_module_nets_connect_pb_type_ports(
   ModuleManager& module_manager, const ModuleId& grid_module,
   const ModuleId& child_module, const size_t& child_instance,
   const t_sub_tile& sub_tile, const VprDeviceAnnotation& vpr_device_annotation,
-  t_physical_tile_type_ptr grid_type_descriptor, const e_side& border_side) {
+  t_physical_tile_type_ptr grid_type_descriptor,
+  const TileAnnotation& tile_annotation, const e_side& border_side) {
   /* Ensure that we have a valid grid_type_descriptor */
   VTR_ASSERT(nullptr != grid_type_descriptor);
 
@@ -129,8 +141,8 @@ static void add_grid_module_nets_connect_pb_type_ports(
       add_grid_module_net_connect_pb_graph_pin(
         module_manager, grid_module, child_module, child_instance,
         child_inst_subtile_index, vpr_device_annotation, grid_type_descriptor,
-        &(top_pb_graph_node->input_pins[iport][ipin]), border_side,
-        INPUT2INPUT_INTERC);
+        tile_annotation, &(top_pb_graph_node->input_pins[iport][ipin]),
+        border_side, INPUT2INPUT_INTERC);
     }
   }
 
@@ -140,8 +152,8 @@ static void add_grid_module_nets_connect_pb_type_ports(
       add_grid_module_net_connect_pb_graph_pin(
         module_manager, grid_module, child_module, child_instance,
         child_inst_subtile_index, vpr_device_annotation, grid_type_descriptor,
-        &(top_pb_graph_node->output_pins[iport][ipin]), border_side,
-        OUTPUT2OUTPUT_INTERC);
+        tile_annotation, &(top_pb_graph_node->output_pins[iport][ipin]),
+        border_side, OUTPUT2OUTPUT_INTERC);
     }
   }
 
@@ -151,8 +163,8 @@ static void add_grid_module_nets_connect_pb_type_ports(
       add_grid_module_net_connect_pb_graph_pin(
         module_manager, grid_module, child_module, child_instance,
         child_inst_subtile_index, vpr_device_annotation, grid_type_descriptor,
-        &(top_pb_graph_node->clock_pins[iport][ipin]), border_side,
-        INPUT2INPUT_INTERC);
+        tile_annotation, &(top_pb_graph_node->clock_pins[iport][ipin]),
+        border_side, INPUT2INPUT_INTERC);
     }
   }
 }
@@ -1151,8 +1163,9 @@ static int build_physical_tile_module(
   const CircuitLibrary& circuit_lib,
   const e_config_protocol_type& sram_orgz_type,
   const CircuitModelId& sram_model, t_physical_tile_type_ptr phy_block_type,
-  const e_side& border_side, const bool& duplicate_grid_pin,
-  const bool& group_config_block, const bool& verbose) {
+  const TileAnnotation& tile_annotation, const e_side& border_side,
+  const bool& duplicate_grid_pin, const bool& group_config_block,
+  const bool& verbose) {
   int status = CMD_EXEC_SUCCESS;
   /* Create a Module for the top-level physical block, and add to module manager
    */
@@ -1231,7 +1244,7 @@ static int build_physical_tile_module(
     /* Default way to add these ports by following the definition in pb_types */
     add_grid_module_pb_type_ports(module_manager, grid_module,
                                   vpr_device_annotation, phy_block_type,
-                                  border_side);
+                                  tile_annotation, border_side);
     /* Add module nets to connect the pb_type ports to sub modules */
     for (const t_sub_tile& sub_tile : phy_block_type->sub_tiles) {
       VTR_ASSERT(sub_tile.equivalent_sites.size() == 1);
@@ -1248,15 +1261,15 @@ static int build_physical_tile_module(
            module_manager.child_module_instances(grid_module, pb_module)) {
         add_grid_module_nets_connect_pb_type_ports(
           module_manager, grid_module, pb_module, child_instance, sub_tile,
-          vpr_device_annotation, phy_block_type, border_side);
+          vpr_device_annotation, phy_block_type, tile_annotation, border_side);
       }
     }
   } else {
     VTR_ASSERT_SAFE(true == duplicate_grid_pin);
     /* Add these ports with duplication */
-    add_grid_module_duplicated_pb_type_ports(module_manager, grid_module,
-                                             vpr_device_annotation,
-                                             phy_block_type, border_side);
+    add_grid_module_duplicated_pb_type_ports(
+      module_manager, grid_module, vpr_device_annotation, phy_block_type,
+      tile_annotation, border_side);
 
     /* Add module nets to connect the duplicated pb_type ports to sub modules */
     for (const t_sub_tile& sub_tile : phy_block_type->sub_tiles) {
@@ -1274,7 +1287,7 @@ static int build_physical_tile_module(
            module_manager.child_module_instances(grid_module, pb_module)) {
         add_grid_module_nets_connect_duplicated_pb_type_ports(
           module_manager, grid_module, pb_module, child_instance, sub_tile,
-          vpr_device_annotation, phy_block_type, border_side);
+          vpr_device_annotation, phy_block_type, tile_annotation, border_side);
       }
     }
   }
@@ -1357,6 +1370,7 @@ int build_grid_modules(
   ModuleManager& module_manager, DecoderLibrary& decoder_lib,
   const DeviceContext& device_ctx, const VprDeviceAnnotation& device_annotation,
   const CircuitLibrary& circuit_lib, const MuxLibrary& mux_lib,
+  const TileAnnotation& tile_annotation,
   const e_config_protocol_type& sram_orgz_type,
   const CircuitModelId& sram_model, const bool& duplicate_grid_pin,
   const bool& group_config_block, const bool& verbose) {
@@ -1414,8 +1428,8 @@ int build_grid_modules(
       for (const e_side& io_type_side : io_type_sides) {
         status = build_physical_tile_module(
           module_manager, decoder_lib, device_annotation, circuit_lib,
-          sram_orgz_type, sram_model, &physical_tile, io_type_side,
-          duplicate_grid_pin, group_config_block, verbose);
+          sram_orgz_type, sram_model, &physical_tile, tile_annotation,
+          io_type_side, duplicate_grid_pin, group_config_block, verbose);
         if (status != CMD_EXEC_SUCCESS) {
           return CMD_EXEC_FATAL_ERROR;
         }
@@ -1424,7 +1438,7 @@ int build_grid_modules(
       /* For CLB and heterogenenous blocks */
       status = build_physical_tile_module(
         module_manager, decoder_lib, device_annotation, circuit_lib,
-        sram_orgz_type, sram_model, &physical_tile, NUM_SIDES,
+        sram_orgz_type, sram_model, &physical_tile, tile_annotation, NUM_SIDES,
         duplicate_grid_pin, group_config_block, verbose);
       if (status != CMD_EXEC_SUCCESS) {
         return CMD_EXEC_FATAL_ERROR;
diff --git a/openfpga/src/fabric/build_grid_modules.h b/openfpga/src/fabric/build_grid_modules.h
index d83cc3ac3..996b9bda2 100644
--- a/openfpga/src/fabric/build_grid_modules.h
+++ b/openfpga/src/fabric/build_grid_modules.h
@@ -7,6 +7,7 @@
 #include "decoder_library.h"
 #include "module_manager.h"
 #include "mux_library.h"
+#include "tile_annotation.h"
 #include "vpr_context.h"
 #include "vpr_device_annotation.h"
 
@@ -21,6 +22,7 @@ int build_grid_modules(
   ModuleManager& module_manager, DecoderLibrary& decoder_lib,
   const DeviceContext& device_ctx, const VprDeviceAnnotation& device_annotation,
   const CircuitLibrary& circuit_lib, const MuxLibrary& mux_lib,
+  const TileAnnotation& tile_annotation,
   const e_config_protocol_type& sram_orgz_type,
   const CircuitModelId& sram_model, const bool& duplicate_grid_pin,
   const bool& group_config_block, const bool& verbose);
diff --git a/openfpga/src/fabric/build_tile_modules.cpp b/openfpga/src/fabric/build_tile_modules.cpp
index 6fafbcf3d..caf82f075 100644
--- a/openfpga/src/fabric/build_tile_modules.cpp
+++ b/openfpga/src/fabric/build_tile_modules.cpp
@@ -1004,9 +1004,10 @@ static int build_tile_port_and_nets_from_pb(
   ModuleManager& module_manager, const ModuleId& tile_module,
   const DeviceGrid& grids, const size_t& layer,
   const VprDeviceAnnotation& vpr_device_annotation, const RRGraphView& rr_graph,
-  const vtr::Point<size_t>& pb_coord, const std::vector<size_t>& pb_instances,
-  const FabricTile& fabric_tile, const FabricTileId& curr_fabric_tile_id,
-  const size_t& ipb, const bool& frame_view, const bool& verbose) {
+  const TileAnnotation& tile_annotation, const vtr::Point<size_t>& pb_coord,
+  const std::vector<size_t>& pb_instances, const FabricTile& fabric_tile,
+  const FabricTileId& curr_fabric_tile_id, const size_t& ipb,
+  const bool& frame_view, const bool& verbose) {
   size_t pb_instance = pb_instances[ipb];
   t_physical_tile_type_ptr phy_tile = grids.get_physical_type(
     t_physical_tile_loc(pb_coord.x(), pb_coord.y(), layer));
@@ -1065,6 +1066,14 @@ static int build_tile_port_and_nets_from_pb(
                      subtile_index < phy_tile->capacity);
           std::string port_name = generate_grid_port_name(
             iwidth, iheight, subtile_index, side, pin_info);
+          if (tile_annotation.is_tile_port_to_merge(std::string(phy_tile->name),
+                                                    pin_info.get_name())) {
+            if (subtile_index == 0) {
+              port_name = generate_grid_port_name(0, 0, 0, TOP, pin_info);
+            } else {
+              continue;
+            }
+          }
           BasicPort pb_port(port_name, 0, 0);
           ModulePortId pb_module_port_id =
             module_manager.find_module_port(pb_module, port_name);
@@ -1193,8 +1202,8 @@ static int build_tile_module_ports_and_nets(
   const DeviceGrid& grids, const size_t& layer,
   const VprDeviceAnnotation& vpr_device_annotation,
   const DeviceRRGSB& device_rr_gsb, const RRGraphView& rr_graph_view,
-  const FabricTile& fabric_tile, const FabricTileId& fabric_tile_id,
-  const std::vector<size_t>& pb_instances,
+  const TileAnnotation& tile_annotation, const FabricTile& fabric_tile,
+  const FabricTileId& fabric_tile_id, const std::vector<size_t>& pb_instances,
   const std::map<t_rr_type, std::vector<size_t>>& cb_instances,
   const std::vector<size_t>& sb_instances, const bool& name_module_using_index,
   const bool& frame_view, const bool& verbose) {
@@ -1259,8 +1268,8 @@ static int build_tile_module_ports_and_nets(
       fabric_tile.pb_coordinates(fabric_tile_id)[ipb];
     status_code = build_tile_port_and_nets_from_pb(
       module_manager, tile_module, grids, layer, vpr_device_annotation,
-      rr_graph_view, pb_coord, pb_instances, fabric_tile, fabric_tile_id, ipb,
-      frame_view, verbose);
+      rr_graph_view, tile_annotation, pb_coord, pb_instances, fabric_tile,
+      fabric_tile_id, ipb, frame_view, verbose);
     if (status_code != CMD_EXEC_SUCCESS) {
       return CMD_EXEC_FATAL_ERROR;
     }
@@ -1303,7 +1312,8 @@ static int build_tile_module(
   const DeviceGrid& grids, const size_t& layer,
   const VprDeviceAnnotation& vpr_device_annotation,
   const DeviceRRGSB& device_rr_gsb, const RRGraphView& rr_graph_view,
-  const CircuitLibrary& circuit_lib, const CircuitModelId& sram_model,
+  const TileAnnotation& tile_annotation, const CircuitLibrary& circuit_lib,
+  const CircuitModelId& sram_model,
   const e_config_protocol_type& sram_orgz_type,
   const bool& name_module_using_index, const bool& frame_view,
   const bool& verbose) {
@@ -1451,8 +1461,9 @@ static int build_tile_module(
   /* Add module nets and ports */
   status_code = build_tile_module_ports_and_nets(
     module_manager, tile_module, grids, layer, vpr_device_annotation,
-    device_rr_gsb, rr_graph_view, fabric_tile, fabric_tile_id, pb_instances,
-    cb_instances, sb_instances, name_module_using_index, frame_view, verbose);
+    device_rr_gsb, rr_graph_view, tile_annotation, fabric_tile, fabric_tile_id,
+    pb_instances, cb_instances, sb_instances, name_module_using_index,
+    frame_view, verbose);
 
   /* Add global ports to the pb_module:
    * This is a much easier job after adding sub modules (instances),
@@ -1521,6 +1532,7 @@ int build_tile_modules(ModuleManager& module_manager,
                        const VprDeviceAnnotation& vpr_device_annotation,
                        const DeviceRRGSB& device_rr_gsb,
                        const RRGraphView& rr_graph_view,
+                       const TileAnnotation& tile_annotation,
                        const CircuitLibrary& circuit_lib,
                        const CircuitModelId& sram_model,
                        const e_config_protocol_type& sram_orgz_type,
@@ -1536,8 +1548,9 @@ int build_tile_modules(ModuleManager& module_manager,
   for (FabricTileId fabric_tile_id : fabric_tile.unique_tiles()) {
     status_code = build_tile_module(
       module_manager, decoder_lib, fabric_tile, fabric_tile_id, grids, layer,
-      vpr_device_annotation, device_rr_gsb, rr_graph_view, circuit_lib,
-      sram_model, sram_orgz_type, name_module_using_index, frame_view, verbose);
+      vpr_device_annotation, device_rr_gsb, rr_graph_view, tile_annotation,
+      circuit_lib, sram_model, sram_orgz_type, name_module_using_index,
+      frame_view, verbose);
     if (status_code != CMD_EXEC_SUCCESS) {
       return CMD_EXEC_FATAL_ERROR;
     }
diff --git a/openfpga/src/fabric/build_tile_modules.h b/openfpga/src/fabric/build_tile_modules.h
index 62f9cbe99..83f219610 100644
--- a/openfpga/src/fabric/build_tile_modules.h
+++ b/openfpga/src/fabric/build_tile_modules.h
@@ -15,6 +15,7 @@
 #include "fabric_tile.h"
 #include "module_manager.h"
 #include "rr_graph_view.h"
+#include "tile_annotation.h"
 #include "vpr_device_annotation.h"
 
 /********************************************************************
@@ -30,6 +31,7 @@ int build_tile_modules(ModuleManager& module_manager,
                        const VprDeviceAnnotation& vpr_device_annotation,
                        const DeviceRRGSB& device_rr_gsb,
                        const RRGraphView& rr_graph_view,
+                       const TileAnnotation& tile_annotation,
                        const CircuitLibrary& circuit_lib,
                        const CircuitModelId& sram_model,
                        const e_config_protocol_type& sram_orgz_type,
diff --git a/openfpga/src/fabric/build_top_module_child_tile_instance.cpp b/openfpga/src/fabric/build_top_module_child_tile_instance.cpp
index b4bc5e8c2..3c1c86c1c 100644
--- a/openfpga/src/fabric/build_top_module_child_tile_instance.cpp
+++ b/openfpga/src/fabric/build_top_module_child_tile_instance.cpp
@@ -1404,6 +1404,15 @@ static int build_top_module_global_net_for_given_tile_module(
           std::string grid_port_name =
             generate_grid_port_name(grid_pin_width, grid_pin_height,
                                     subtile_index, pin_side, grid_pin_info);
+          if (tile_annotation.is_tile_port_to_merge(
+                std::string(physical_tile->name), grid_pin_info.get_name())) {
+            if (subtile_index == 0) {
+              grid_port_name =
+                generate_grid_port_name(0, 0, 0, TOP, grid_pin_info);
+            } else {
+              continue;
+            }
+          }
           std::string tile_grid_port_name =
             generate_tile_module_port_name(grid_instance_name, grid_port_name);
           ModulePortId tile_grid_port_id =
diff --git a/openfpga/src/fabric/build_top_module_connection.cpp b/openfpga/src/fabric/build_top_module_connection.cpp
index d49a6f1cf..98b256fe0 100644
--- a/openfpga/src/fabric/build_top_module_connection.cpp
+++ b/openfpga/src/fabric/build_top_module_connection.cpp
@@ -950,6 +950,16 @@ static int build_top_module_global_net_for_given_grid_module(
           std::string grid_port_name =
             generate_grid_port_name(grid_pin_width, grid_pin_height,
                                     subtile_index, pin_side, grid_pin_info);
+          if (tile_annotation.is_tile_port_to_merge(
+                std::string(physical_tile->name), grid_pin_info.get_name())) {
+            if (subtile_index == 0) {
+              grid_port_name =
+                generate_grid_port_name(0, 0, 0, TOP, grid_pin_info);
+            } else {
+              continue;
+            }
+          }
+
           ModulePortId grid_port_id =
             module_manager.find_module_port(grid_module, grid_port_name);
           VTR_ASSERT(true == module_manager.valid_module_port_id(grid_module,
diff --git a/openfpga_flow/openfpga_arch/k4_N4_40nm_GlobalTileClkMergeSubtilePort_registerable_io_cc_openfpga.xml b/openfpga_flow/openfpga_arch/k4_N4_40nm_GlobalTileClkMergeSubtilePort_registerable_io_cc_openfpga.xml
new file mode 100644
index 000000000..a7c1a8bfa
--- /dev/null
+++ b/openfpga_flow/openfpga_arch/k4_N4_40nm_GlobalTileClkMergeSubtilePort_registerable_io_cc_openfpga.xml
@@ -0,0 +1,215 @@
+<?xml version="1.0"?>
+<!-- Architecture annotation for OpenFPGA framework
+     This annotation supports the k6_N10_40nm.xml 
+     - General purpose logic block
+       - K = 6, N = 10, I = 40
+       - Single mode
+     - Routing architecture
+       - L = 4, fc_in = 0.15, fc_out = 0.1
+  -->
+<openfpga_architecture>
+  <technology_library>
+    <device_library>
+      <device_model name="logic" type="transistor">
+        <lib type="industry" corner="TOP_TT" ref="M" path="${OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.pm"/>
+        <design vdd="0.9" pn_ratio="2"/>
+        <pmos name="pch" chan_length="40e-9" min_width="140e-9" variation="logic_transistor_var"/>
+        <nmos name="nch" chan_length="40e-9" min_width="140e-9" variation="logic_transistor_var"/>
+      </device_model>
+      <device_model name="io" type="transistor">
+        <lib type="academia" ref="M" path="${OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.pm"/>
+        <design vdd="2.5" pn_ratio="3"/>
+        <pmos name="pch_25" chan_length="270e-9" min_width="320e-9" variation="io_transistor_var"/>
+        <nmos name="nch_25" chan_length="270e-9" min_width="320e-9" variation="io_transistor_var"/>
+      </device_model>
+    </device_library>
+    <variation_library>
+      <variation name="logic_transistor_var" abs_deviation="0.1" num_sigma="3"/>
+      <variation name="io_transistor_var" abs_deviation="0.1" num_sigma="3"/>
+    </variation_library>
+  </technology_library>
+  <circuit_library>
+    <circuit_model type="inv_buf" name="INVTX1" prefix="INVTX1" is_default="true">
+      <design_technology type="cmos" topology="inverter" size="1"/>
+      <device_technology device_model_name="logic"/>
+      <port type="input" prefix="in" size="1"/>
+      <port type="output" prefix="out" size="1"/>
+      <delay_matrix type="rise" in_port="in" out_port="out">
+        10e-12
+      </delay_matrix>
+      <delay_matrix type="fall" in_port="in" out_port="out">
+        10e-12
+      </delay_matrix>
+    </circuit_model>
+    <circuit_model type="inv_buf" name="buf4" prefix="buf4" is_default="false">
+      <design_technology type="cmos" topology="buffer" size="1" num_level="2" f_per_stage="4"/>
+      <device_technology device_model_name="logic"/>
+      <port type="input" prefix="in" size="1"/>
+      <port type="output" prefix="out" size="1"/>
+      <delay_matrix type="rise" in_port="in" out_port="out">
+        10e-12
+      </delay_matrix>
+      <delay_matrix type="fall" in_port="in" out_port="out">
+        10e-12
+      </delay_matrix>
+    </circuit_model>
+    <circuit_model type="inv_buf" name="tap_buf4" prefix="tap_buf4" is_default="false">
+      <design_technology type="cmos" topology="buffer" size="1" num_level="3" f_per_stage="4"/>
+      <device_technology device_model_name="logic"/>
+      <port type="input" prefix="in" size="1"/>
+      <port type="output" prefix="out" size="1"/>
+      <delay_matrix type="rise" in_port="in" out_port="out">
+        10e-12
+      </delay_matrix>
+      <delay_matrix type="fall" in_port="in" out_port="out">
+        10e-12
+      </delay_matrix>
+    </circuit_model>
+    <circuit_model type="pass_gate" name="TGATE" prefix="TGATE" is_default="true">
+      <design_technology type="cmos" topology="transmission_gate" nmos_size="1" pmos_size="2"/>
+      <device_technology device_model_name="logic"/>
+      <input_buffer exist="false"/>
+      <output_buffer exist="false"/>
+      <port type="input" prefix="in" size="1"/>
+      <port type="input" prefix="sel" size="1"/>
+      <port type="input" prefix="selb" size="1"/>
+      <port type="output" prefix="out" size="1"/>
+      <delay_matrix type="rise" in_port="in sel selb" out_port="out">
+        10e-12 5e-12 5e-12
+      </delay_matrix>
+      <delay_matrix type="fall" in_port="in sel selb" out_port="out">
+        10e-12 5e-12 5e-12
+      </delay_matrix>
+    </circuit_model>
+    <circuit_model type="chan_wire" name="chan_segment" prefix="track_seg" is_default="true">
+      <design_technology type="cmos"/>
+      <input_buffer exist="false"/>
+      <output_buffer exist="false"/>
+      <port type="input" prefix="in" size="1"/>
+      <port type="output" prefix="out" size="1"/>
+      <wire_param model_type="pi" R="101" C="22.5e-15" num_level="1"/>
+      <!-- model_type could be T, res_val and cap_val DON'T CARE -->
+    </circuit_model>
+    <circuit_model type="wire" name="direct_interc" prefix="direct_interc" is_default="true">
+      <design_technology type="cmos"/>
+      <input_buffer exist="false"/>
+      <output_buffer exist="false"/>
+      <port type="input" prefix="in" size="1"/>
+      <port type="output" prefix="out" size="1"/>
+      <wire_param model_type="pi" R="0" C="0" num_level="1"/>
+      <!-- model_type could be T, res_val cap_val should be defined -->
+    </circuit_model>
+    <circuit_model type="mux" name="mux_tree" prefix="mux_tree" dump_structural_verilog="true">
+      <design_technology type="cmos" structure="tree" add_const_input="true" const_input_val="1"/>
+      <input_buffer exist="true" circuit_model_name="INVTX1"/>
+      <output_buffer exist="true" circuit_model_name="INVTX1"/>
+      <pass_gate_logic circuit_model_name="TGATE"/>
+      <port type="input" prefix="in" size="1"/>
+      <port type="output" prefix="out" size="1"/>
+      <port type="sram" prefix="sram" size="1"/>
+    </circuit_model>
+    <circuit_model type="mux" name="mux_tree_tapbuf" prefix="mux_tree_tapbuf" is_default="true" dump_structural_verilog="true">
+      <design_technology type="cmos" structure="tree" add_const_input="true" const_input_val="1"/>
+      <input_buffer exist="true" circuit_model_name="INVTX1"/>
+      <output_buffer exist="true" circuit_model_name="tap_buf4"/>
+      <pass_gate_logic circuit_model_name="TGATE"/>
+      <port type="input" prefix="in" size="1"/>
+      <port type="output" prefix="out" size="1"/>
+      <port type="sram" prefix="sram" size="1"/>
+    </circuit_model>
+    <!--DFF subckt ports should be defined as <D> <Q> <CLK> <RESET> <SET>  -->
+    <circuit_model type="ff" name="DFFSRQ" prefix="DFFSRQ" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/openfpga_cell_library/spice/dff.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/openfpga_cell_library/verilog/dff.v">
+      <design_technology type="cmos"/>
+      <input_buffer exist="true" circuit_model_name="INVTX1"/>
+      <output_buffer exist="true" circuit_model_name="INVTX1"/>
+      <port type="input" prefix="D" size="1"/>
+      <port type="input" prefix="set" lib_name="SET" size="1" is_global="true" default_val="0" is_set="true"/>
+      <port type="input" prefix="reset" lib_name="RST" size="1" is_global="true" default_val="0" is_reset="true"/>
+      <port type="output" prefix="Q" size="1"/>
+      <port type="clock" prefix="clk" lib_name="CK" size="1" is_global="false" default_val="0"/>
+    </circuit_model>
+    <circuit_model type="lut" name="lut4" prefix="lut4" dump_structural_verilog="true">
+      <design_technology type="cmos"/>
+      <input_buffer exist="true" circuit_model_name="INVTX1"/>
+      <output_buffer exist="true" circuit_model_name="INVTX1"/>
+      <lut_input_inverter exist="true" circuit_model_name="INVTX1"/>
+      <lut_input_buffer exist="true" circuit_model_name="buf4"/>
+      <pass_gate_logic circuit_model_name="TGATE"/>
+      <port type="input" prefix="in" size="4"/>
+      <port type="output" prefix="out" size="1"/>
+      <port type="sram" prefix="sram" size="16"/>
+    </circuit_model>
+    <!--Scan-chain DFF subckt ports should be defined as <D> <Q> <Qb> <CLK> <RESET> <SET>  -->
+    <circuit_model type="ccff" name="DFF" prefix="DFF" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/openfpga_cell_library/spice/dff.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/openfpga_cell_library/verilog/dff.v">
+      <design_technology type="cmos"/>
+      <input_buffer exist="true" circuit_model_name="INVTX1"/>
+      <output_buffer exist="true" circuit_model_name="INVTX1"/>
+      <port type="input" prefix="D" size="1"/>
+      <port type="output" prefix="Q" size="1"/>
+      <port type="output" prefix="QN" size="1"/>
+      <port type="clock" prefix="prog_clk" lib_name="CK" size="1" is_global="true" default_val="0" is_prog="true"/>
+    </circuit_model>
+    <circuit_model type="iopad" name="GPIO" prefix="GPIO" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/openfpga_cell_library/spice/gpio.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/openfpga_cell_library/verilog/gpio.v">
+      <design_technology type="cmos"/>
+      <input_buffer exist="true" circuit_model_name="INVTX1"/>
+      <output_buffer exist="true" circuit_model_name="INVTX1"/>
+      <port type="inout" prefix="PAD" size="1" is_global="true" is_io="true" is_data_io="true"/>
+      <port type="sram" prefix="DIR" size="1" mode_select="true" circuit_model_name="DFF" default_val="1"/>
+      <port type="input" prefix="outpad" lib_name="A" size="1"/>
+      <port type="output" prefix="inpad" lib_name="Y" size="1"/>
+    </circuit_model>
+    <circuit_model type="iopad" name="GPIN" prefix="GPIN" is_default="true" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/openfpga_cell_library/verilog/gpio.v">
+      <design_technology type="cmos"/>
+      <input_buffer exist="true" circuit_model_name="sky130_fd_sc_hd__inv_1"/>
+      <output_buffer exist="true" circuit_model_name="sky130_fd_sc_hd__inv_1"/>
+      <port type="inout" prefix="PAD" lib_name="A" size="1" is_global="true" is_io="true" is_data_io="true"/>
+      <port type="output" prefix="inpad" lib_name="Y" size="1"/>
+    </circuit_model>
+  </circuit_library>
+  <configuration_protocol>
+    <organization type="scan_chain" circuit_model_name="DFF"/>
+  </configuration_protocol>
+  <connection_block>
+    <switch name="ipin_cblock" circuit_model_name="mux_tree_tapbuf"/>
+  </connection_block>
+  <switch_block>
+    <switch name="0" circuit_model_name="mux_tree_tapbuf"/>
+  </switch_block>
+  <routing_segment>
+    <segment name="L4" circuit_model_name="chan_segment"/>
+  </routing_segment>
+  <tile_annotations>
+    <merge_subtile_ports tile="io_hybrid" port="clk"/>
+    <global_port name="clk" is_clock="true" default_val="0">
+      <tile name="clb" port="clk" x="-1" y="-1"/>
+      <tile name="io" port="clk" x="-1" y="-1"/>
+      <tile name="io_hybrid" port="clk" x="-1" y="-1"/>
+    </global_port>
+  </tile_annotations>
+  <pb_type_annotations>
+    <!-- physical pb_type binding in complex block IO -->
+    <pb_type name="io" physical_mode_name="physical" idle_mode_name="inpad"/>
+    <pb_type name="io[physical].iopad" circuit_model_name="GPIO" mode_bits="1"/>
+    <pb_type name="io[physical].ff" circuit_model_name="DFFSRQ"/>
+    <pb_type name="io[inpad].inpad" physical_pb_type_name="io[physical].iopad" mode_bits="1"/>
+    <pb_type name="io[inpad_registered].inpad" physical_pb_type_name="io[physical].iopad" mode_bits="1"/>
+    <pb_type name="io[inpad_registered].ff" physical_pb_type_name="io[physical].ff"/>
+    <pb_type name="io[outpad].outpad" physical_pb_type_name="io[physical].iopad" mode_bits="0"/>
+    <pb_type name="io_input" physical_mode_name="physical" idle_mode_name="inpad"/>
+    <pb_type name="io_input[physical].iopad" circuit_model_name="GPIN" mode_bits="1"/>
+    <pb_type name="io_input[physical].ff" circuit_model_name="DFFSRQ"/>
+    <pb_type name="io_input[inpad].inpad" physical_pb_type_name="io_input[physical].iopad" mode_bits="1"/>
+    <pb_type name="io_input[inpad_registered].inpad" physical_pb_type_name="io_input[physical].iopad" mode_bits="1"/>
+    <pb_type name="io_input[inpad_registered].ff" physical_pb_type_name="io_input[physical].ff"/>
+    <!-- End physical pb_type binding in complex block IO -->
+    <!-- physical pb_type binding in complex block CLB -->
+    <!-- physical mode will be the default mode if not specified -->
+    <pb_type name="clb">
+      <!-- Binding interconnect to circuit models as their physical implementation, if not defined, we use the default model -->
+      <interconnect name="crossbar" circuit_model_name="mux_tree"/>
+    </pb_type>
+    <pb_type name="clb.fle[n1_lut4].ble4.lut4" circuit_model_name="lut4"/>
+    <pb_type name="clb.fle[n1_lut4].ble4.ff" circuit_model_name="DFFSRQ"/>
+    <!-- End physical pb_type binding in complex block IO -->
+  </pb_type_annotations>
+</openfpga_architecture>
diff --git a/openfpga_flow/openfpga_shell_scripts/global_tile_clock_options_full_testbench_example_script.openfpga b/openfpga_flow/openfpga_shell_scripts/global_tile_clock_options_full_testbench_example_script.openfpga
new file mode 100644
index 000000000..956451380
--- /dev/null
+++ b/openfpga_flow/openfpga_shell_scripts/global_tile_clock_options_full_testbench_example_script.openfpga
@@ -0,0 +1,63 @@
+# Run VPR for the 'and' design
+# When the global clock is defined as a port of a tile, clock routing in VPR should be skipped
+# This is due to the Fc_in of clock port is set to 0 for global wiring
+#--write_rr_graph example_rr_graph.xml
+vpr ${VPR_ARCH_FILE} ${VPR_TESTBENCH_BLIF} --device ${OPENFPGA_VPR_DEVICE_LAYOUT}
+
+# 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 Look-Up Table truth tables based on packing results
+lut_truth_table_fixup
+
+# Build the module graph
+#  - Enabled compression on routing architecture modules
+#  - Enable pin duplication on grid modules
+build_fabric --compress_routing ${OPENFPGA_GROUP_CONFIG_BLOCK_OPTIONS} ${OPENFPGA_GROUP_TILE_CONFIG_OPTIONS}  #--verbose
+
+# Write the fabric hierarchy of module graph to a file
+# This is used by hierarchical PnR flows
+write_fabric_hierarchy --file ./fabric_hierarchy.txt
+
+# 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_independent_bitstream.xml
+
+# Build fabric-dependent bitstream
+build_fabric_bitstream --verbose
+
+# Write fabric-dependent bitstream
+write_fabric_bitstream --file fabric_bitstream.bit --format plain_text
+
+# Write the Verilog netlist for FPGA fabric
+#  - Enable the use of explicit port mapping in Verilog netlist
+write_fabric_verilog --file ./SRC --explicit_port_mapping --include_timing --print_user_defined_template --verbose
+
+# Write the Verilog testbench for FPGA fabric
+#  - We suggest the use of same output directory as fabric Verilog netlists
+#  - Must specify the reference benchmark file if you want to output any testbenches
+#  - Enable top-level testbench which is a full verification including programming circuit and core logic of FPGA
+#  - Enable pre-configured top-level testbench which is a fast verification skipping programming phase
+#  - Simulation ini file is optional and is needed only when you need to interface different HDL simulators using openfpga flow-run scripts
+write_full_testbench --file ./SRC --reference_benchmark_file_path ${REFERENCE_VERILOG_TESTBENCH} --explicit_port_mapping --include_signal_init --bitstream fabric_bitstream.bit
+
+# 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/regression_test_scripts/basic_reg_test.sh b/openfpga_flow/regression_test_scripts/basic_reg_test.sh
index 4835a66cd..dd945b427 100755
--- a/openfpga_flow/regression_test_scripts/basic_reg_test.sh
+++ b/openfpga_flow/regression_test_scripts/basic_reg_test.sh
@@ -211,6 +211,8 @@ run-task basic_tests/module_naming/renaming_rules_on_indexed_names $@
 echo -e "Testing global port definition from tiles";
 run-task basic_tests/global_tile_ports/global_tile_clock $@
 run-task basic_tests/global_tile_ports/global_tile_clock_subtile $@
+run-task basic_tests/global_tile_ports/global_tile_clock_subtile_port_merge $@
+run-task basic_tests/global_tile_ports/global_tile_clock_subtile_port_merge_fabric_tile_group_config $@
 run-task basic_tests/global_tile_ports/global_tile_reset $@
 run-task basic_tests/global_tile_ports/global_tile_4clock $@
 run-task basic_tests/global_tile_ports/global_tile_4clock_pin $@
diff --git a/openfpga_flow/tasks/basic_tests/global_tile_ports/global_tile_clock_subtile_port_merge/config/task.conf b/openfpga_flow/tasks/basic_tests/global_tile_ports/global_tile_clock_subtile_port_merge/config/task.conf
new file mode 100644
index 000000000..adbbaa2cb
--- /dev/null
+++ b/openfpga_flow/tasks/basic_tests/global_tile_ports/global_tile_clock_subtile_port_merge/config/task.conf
@@ -0,0 +1,35 @@
+# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
+# 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
+power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
+power_analysis = true
+spice_output=false
+verilog_output=true
+timeout_each_job = 20*60
+fpga_flow=yosys_vpr
+
+[OpenFPGA_SHELL]
+openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_shell_scripts/global_tile_clock_full_testbench_example_script.openfpga
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k4_N4_40nm_GlobalTileClkMergeSubtilePort_registerable_io_cc_openfpga.xml
+openfpga_sim_setting_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_simulation_settings/auto_sim_openfpga.xml
+openfpga_vpr_device_layout=2x2_hybrid_io
+
+[ARCHITECTURES]
+arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/vpr_arch/k4_N4_tileable_GlobalTileClk_registerable_io_40nm.xml
+
+[BENCHMARKS]
+bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and2_pipelined/and2_pipelined.v
+
+[SYNTHESIS_PARAM]
+bench_read_verilog_options_common = -nolatches
+bench0_top = and2_pipelined
+
+[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
+end_flow_with_test=
diff --git a/openfpga_flow/tasks/basic_tests/global_tile_ports/global_tile_clock_subtile_port_merge_fabric_tile_group_config/config/task.conf b/openfpga_flow/tasks/basic_tests/global_tile_ports/global_tile_clock_subtile_port_merge_fabric_tile_group_config/config/task.conf
new file mode 100644
index 000000000..dc9eacdb7
--- /dev/null
+++ b/openfpga_flow/tasks/basic_tests/global_tile_ports/global_tile_clock_subtile_port_merge_fabric_tile_group_config/config/task.conf
@@ -0,0 +1,37 @@
+# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
+# 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
+power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
+power_analysis = true
+spice_output=false
+verilog_output=true
+timeout_each_job = 20*60
+fpga_flow=yosys_vpr
+
+[OpenFPGA_SHELL]
+openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_shell_scripts/global_tile_clock_options_full_testbench_example_script.openfpga
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k4_N4_40nm_GlobalTileClkMergeSubtilePort_registerable_io_cc_openfpga.xml
+openfpga_sim_setting_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_simulation_settings/auto_sim_openfpga.xml
+openfpga_vpr_device_layout=2x2_hybrid_io
+openfpga_group_tile_config_options=--group_tile ${PATH:TASK_DIR}/config/tile_config.xml
+openfpga_group_config_block_options=--group_config_block
+
+[ARCHITECTURES]
+arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/vpr_arch/k4_N4_tileable_GlobalTileClk_registerable_io_40nm.xml
+
+[BENCHMARKS]
+bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and2_pipelined/and2_pipelined.v
+
+[SYNTHESIS_PARAM]
+bench_read_verilog_options_common = -nolatches
+bench0_top = and2_pipelined
+
+[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
+end_flow_with_test=
diff --git a/openfpga_flow/tasks/basic_tests/global_tile_ports/global_tile_clock_subtile_port_merge_fabric_tile_group_config/config/tile_config.xml b/openfpga_flow/tasks/basic_tests/global_tile_ports/global_tile_clock_subtile_port_merge_fabric_tile_group_config/config/tile_config.xml
new file mode 100644
index 000000000..1a1f3f6e8
--- /dev/null
+++ b/openfpga_flow/tasks/basic_tests/global_tile_ports/global_tile_clock_subtile_port_merge_fabric_tile_group_config/config/tile_config.xml
@@ -0,0 +1 @@
+<tiles style="top_left"/>