From 9222d085cd2f21ed0e84ad86d76fbc5b258dcb94 Mon Sep 17 00:00:00 2001
From: tangxifan <tangxifan@gmail.com>
Date: Fri, 13 Jan 2023 22:04:56 -0800
Subject: [PATCH] [test] now use local clock as one of the pins in a clock bus,
 but connected to global routing

---
 openfpga_flow/openfpga_arch/README.md         |   1 +
 ...N4_fracff_localClkGen_40nm_cc_openfpga.xml | 255 ++++++++++++++++++
 .../k4_series/k4n4_clk_gen/config/task.conf   |   2 +-
 ...ac_N4_tileable_fracff_localClkGen_40nm.xml |  11 +-
 4 files changed, 261 insertions(+), 8 deletions(-)
 create mode 100644 openfpga_flow/openfpga_arch/k4_frac_N4_fracff_localClkGen_40nm_cc_openfpga.xml

diff --git a/openfpga_flow/openfpga_arch/README.md b/openfpga_flow/openfpga_arch/README.md
index e4bd7f1f9..0960d3f2d 100644
--- a/openfpga_flow/openfpga_arch/README.md
+++ b/openfpga_flow/openfpga_arch/README.md
@@ -29,6 +29,7 @@ Note that an OpenFPGA architecture can be applied to multiple VPR architecture f
 - registerable\_io: If I/Os are registerable (can be either combinational or sequential)
 - stdcell: If circuit designs are built with standard cells only
 - tree\_mux: If routing multiplexers are built with a tree-like structure
+- localClkGen: The clock signal of CLB can be generated by internal programmable resources
 - <feature_size>: The technology node which the delay numbers are extracted from.
 - powergate : The FPGA has power-gating techniques applied. If not defined, there is no power-gating.
 - GlobalTile<Int>Clk<Pin>: How many clocks are defined through global ports from physical tiles.
diff --git a/openfpga_flow/openfpga_arch/k4_frac_N4_fracff_localClkGen_40nm_cc_openfpga.xml b/openfpga_flow/openfpga_arch/k4_frac_N4_fracff_localClkGen_40nm_cc_openfpga.xml
new file mode 100644
index 000000000..df8f9b37c
--- /dev/null
+++ b/openfpga_flow/openfpga_arch/k4_frac_N4_fracff_localClkGen_40nm_cc_openfpga.xml
@@ -0,0 +1,255 @@
+<?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="gate" name="OR2" prefix="OR2" is_default="true">
+      <design_technology type="cmos" topology="OR"/>
+      <device_technology device_model_name="logic"/>
+      <input_buffer exist="false"/>
+      <output_buffer exist="false"/>
+      <port type="input" prefix="a" size="1"/>
+      <port type="input" prefix="b" size="1"/>
+      <port type="output" prefix="out" size="1"/>
+      <delay_matrix type="rise" in_port="a b" out_port="out">
+        10e-12 5e-12
+      </delay_matrix>
+      <delay_matrix type="fall" in_port="a b" out_port="out">
+        10e-12 5e-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" lib_name="A" size="1"/>
+      <port type="input" prefix="sel" lib_name="S" size="1"/>
+      <port type="input" prefix="selb" lib_name="SI" size="1"/>
+      <port type="output" prefix="out" lib_name="Y" 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_2level" prefix="mux_2level" dump_structural_verilog="true">
+      <design_technology type="cmos" structure="multi_level" num_level="2" 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_2level_tapbuf" prefix="mux_2level_tapbuf" dump_structural_verilog="true">
+      <design_technology type="cmos" structure="multi_level" num_level="2" 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>
+    <circuit_model type="mux" name="mux_1level_tapbuf" prefix="mux_1level_tapbuf" is_default="true" dump_structural_verilog="true">
+      <design_technology type="cmos" structure="one_level" 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="MULTI_MODE_DFFRQ" prefix="MULTI_MODE_DFFRQ" 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="R" lib_name="RST" size="1" default_val="0"/>
+      <port type="output" prefix="Q" size="1"/>
+      <port type="clock" prefix="C" lib_name="CK" size="1" default_val="0"/>
+      <port type="sram" prefix="mode" size="1" mode_select="true" circuit_model_name="DFFR" default_val="0"/>
+    </circuit_model>
+    <circuit_model type="lut" name="frac_lut4" prefix="frac_lut4" dump_structural_verilog="true">
+      <design_technology type="cmos" fracturable_lut="true"/>
+      <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"/>
+      <lut_intermediate_buffer exist="true" circuit_model_name="buf4" location_map="-1-"/>
+      <pass_gate_logic circuit_model_name="TGATE"/>
+      <port type="input" prefix="in" size="4" tri_state_map="---1" circuit_model_name="OR2"/>
+      <port type="output" prefix="lut3_out" size="2" lut_frac_level="3" lut_output_mask="0,1"/>
+      <port type="output" prefix="lut4_out" size="1" lut_output_mask="0"/>
+      <port type="sram" prefix="sram" size="16"/>
+      <port type="sram" prefix="mode" size="1" mode_select="true" circuit_model_name="DFFR" default_val="1"/>
+    </circuit_model>
+    <!--Scan-chain DFF subckt ports should be defined as <D> <Q> <Qb> <CLK> <RESET> <SET>  -->
+    <circuit_model type="ccff" name="DFFR" prefix="DFFR" 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="pReset" lib_name="RST" size="1" is_global="true" default_val="0" is_reset="true" is_prog="true"/>
+      <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="DFFR" 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_library>
+  <configuration_protocol>
+    <organization type="scan_chain" circuit_model_name="DFFR"/>
+  </configuration_protocol>
+  <connection_block>
+    <switch name="ipin_cblock" circuit_model_name="mux_2level_tapbuf"/>
+  </connection_block>
+  <switch_block>
+    <switch name="0" circuit_model_name="mux_2level_tapbuf"/>
+  </switch_block>
+  <routing_segment>
+    <segment name="L4" circuit_model_name="chan_segment"/>
+  </routing_segment>
+  <tile_annotations>
+    <global_port name="op_clk" tile_port="clb.clk[1]" is_clock="true" default_val="0">
+      <tile name="clb" port="clk[1]"/>
+    </global_port>
+    <global_port name="op_reset" is_reset="true" default_val="0">
+      <tile name="clb" port="reset"/>
+    </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[inpad].inpad" physical_pb_type_name="io[physical].iopad" mode_bits="1"/>
+    <pb_type name="io[outpad].outpad" physical_pb_type_name="io[physical].iopad" mode_bits="0"/>
+    <!-- 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_2level"/>
+    </pb_type>
+    <pb_type name="clb.fle" physical_mode_name="physical"/>
+    <pb_type name="clb.fle[physical].fabric.frac_logic.frac_lut4" circuit_model_name="frac_lut4" mode_bits="0"/>
+    <pb_type name="clb.fle[physical].fabric.ff" circuit_model_name="MULTI_MODE_DFFRQ" mode_bits="0"/>
+    <!-- Binding operating pb_type to physical pb_type -->
+    <pb_type name="clb.fle[n2_lut3].lut3inter.ble3.lut3" physical_pb_type_name="clb.fle[physical].fabric.frac_logic.frac_lut4" mode_bits="1" physical_pb_type_index_factor="0.5">
+      <!-- Binding the lut3 to the first 3 inputs of fracturable lut4 -->
+      <port name="in" physical_mode_port="in[0:2]"/>
+      <port name="out" physical_mode_port="lut3_out[0:0]" physical_mode_pin_rotate_offset="1"/>
+    </pb_type>
+    <pb_type name="clb.fle[n2_lut3].lut3inter.ble3.ff[latch].latch" physical_pb_type_name="clb.fle[physical].fabric.ff" mode_bits="0">
+      <port name="clk" physical_mode_port="C"/>
+    </pb_type>
+    <pb_type name="clb.fle[n2_lut3].lut3inter.ble3.ff[dff].dff" physical_pb_type_name="clb.fle[physical].fabric.ff" mode_bits="0"/>
+    <pb_type name="clb.fle[n2_lut3].lut3inter.ble3.ff[dffr].dffr" physical_pb_type_name="clb.fle[physical].fabric.ff" mode_bits="0"/>
+    <pb_type name="clb.fle[n2_lut3].lut3inter.ble3.ff[dffrn].dffrn" physical_pb_type_name="clb.fle[physical].fabric.ff" mode_bits="1">
+      <port name="RN" physical_mode_port="R"/>
+    </pb_type>
+    <pb_type name="clb.fle[n1_lut4].ble4.lut4" physical_pb_type_name="clb.fle[physical].fabric.frac_logic.frac_lut4" mode_bits="0">
+      <!-- Binding the lut4 to the first 4 inputs of fracturable lut4 -->
+      <port name="in" physical_mode_port="in[0:3]"/>
+      <port name="out" physical_mode_port="lut4_out"/>
+    </pb_type>
+    <pb_type name="clb.fle[n1_lut4].ble4.ff[latch].latch" physical_pb_type_name="clb.fle[physical].fabric.ff" mode_bits="0" physical_pb_type_index_factor="2" physical_pb_type_index_offset="0">
+      <port name="clk" physical_mode_port="C"/>
+    </pb_type>
+    <pb_type name="clb.fle[n1_lut4].ble4.ff[dff].dff" physical_pb_type_name="clb.fle[physical].fabric.ff" mode_bits="0" physical_pb_type_index_factor="2" physical_pb_type_index_offset="0"/>
+    <pb_type name="clb.fle[n1_lut4].ble4.ff[dffr].dffr" physical_pb_type_name="clb.fle[physical].fabric.ff" mode_bits="0" physical_pb_type_index_factor="2" physical_pb_type_index_offset="0"/>
+    <pb_type name="clb.fle[n1_lut4].ble4.ff[dffrn].dffrn" physical_pb_type_name="clb.fle[physical].fabric.ff" mode_bits="1" physical_pb_type_index_factor="2" physical_pb_type_index_offset="0">
+      <port name="RN" physical_mode_port="R"/>
+    </pb_type>
+    <!-- End physical pb_type binding in complex block IO -->
+  </pb_type_annotations>
+</openfpga_architecture>
diff --git a/openfpga_flow/tasks/basic_tests/k4_series/k4n4_clk_gen/config/task.conf b/openfpga_flow/tasks/basic_tests/k4_series/k4n4_clk_gen/config/task.conf
index d889031ed..12ad1855b 100644
--- a/openfpga_flow/tasks/basic_tests/k4_series/k4n4_clk_gen/config/task.conf
+++ b/openfpga_flow/tasks/basic_tests/k4_series/k4n4_clk_gen/config/task.conf
@@ -17,7 +17,7 @@ fpga_flow=yosys_vpr
 
 [OpenFPGA_SHELL]
 openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_shell_scripts/ignore_global_nets_on_pins_example_script.openfpga
-openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k4_frac_N4_fracff_40nm_cc_openfpga.xml
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k4_frac_N4_fracff_localClkGen_40nm_cc_openfpga.xml
 openfpga_sim_setting_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_simulation_settings/fixed_sim_openfpga.xml
 openfpga_repack_design_constraint_file=${PATH:TASK_DIR}/config/repack_design_constraints.xml
 
diff --git a/openfpga_flow/vpr_arch/k4_frac_N4_tileable_fracff_localClkGen_40nm.xml b/openfpga_flow/vpr_arch/k4_frac_N4_tileable_fracff_localClkGen_40nm.xml
index a01191372..9d4d8d737 100644
--- a/openfpga_flow/vpr_arch/k4_frac_N4_tileable_fracff_localClkGen_40nm.xml
+++ b/openfpga_flow/vpr_arch/k4_frac_N4_tileable_fracff_localClkGen_40nm.xml
@@ -101,12 +101,10 @@
         </equivalent_sites>
         <input name="I" num_pins="12" equivalent="full"/>
         <input name="reset" num_pins="1" is_non_clock_global="true"/>
-        <!-- A dedicated clock for locally generated clock signals -->
-        <input name="lclk" num_pins="1" equivalent="none"/>
         <output name="O" num_pins="8" equivalent="none"/>
-        <clock name="clk" num_pins="1"/>
+        <clock name="clk" num_pins="2" equivalent="full"/>
         <fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10">
-          <fc_override port_name="clk" fc_type="frac" fc_val="0"/>
+          <fc_override port_name="clk[1]" fc_type="frac" fc_val="0"/>
           <fc_override port_name="reset" fc_type="frac" fc_val="0"/>
         </fc>
         <pinlocations pattern="spread"/>
@@ -277,9 +275,8 @@
     <pb_type name="clb">
       <input name="I" num_pins="12" equivalent="full"/>
       <input name="reset" num_pins="1"/>
-      <input name="lclk" num_pins="1" equivalent="none"/>
       <output name="O" num_pins="8" equivalent="none"/>
-      <clock name="clk" num_pins="1"/>
+      <clock name="clk" num_pins="2" equivalent="full"/>
       <!-- Describe fracturable logic element.  
              Each fracturable logic element has a 6-LUT that can alternatively operate as two 5-LUTs with shared inputs. 
              The outputs of the fracturable logic element can be optionally registered
@@ -614,7 +611,7 @@
           <delay_constant max="95e-12" in_port="clb.I" out_port="fle[3:0].in"/>
           <delay_constant max="75e-12" in_port="fle[3:0].out" out_port="fle[3:0].in"/>
         </complete>
-        <complete name="clks" input="clb.clk clb.lclk" output="fle[3:0].clk">
+        <complete name="clks" input="clb.clk" output="fle[3:0].clk">
         </complete>
         <complete name="resets" input="clb.reset" output="fle[3:0].reset">
         </complete>