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..c820eb762
--- /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" 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/regression_test_scripts/basic_reg_test.sh b/openfpga_flow/regression_test_scripts/basic_reg_test.sh
index 4835a66cd..c7d0b31a8 100755
--- a/openfpga_flow/regression_test_scripts/basic_reg_test.sh
+++ b/openfpga_flow/regression_test_scripts/basic_reg_test.sh
@@ -211,6 +211,7 @@ 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_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=