From 72749be4bd3153f34965648fae8bb82c616704a7 Mon Sep 17 00:00:00 2001
From: tangxifan <tangxifan@gmail.com>
Date: Tue, 22 Sep 2020 15:31:34 -0600
Subject: [PATCH] [Architecture] Add OpenFPGA architecture for k4n4 with
 fracturable 32-bit multiplier

---
 ...n_mem1K_frac_dsp32_40nm_frame_openfpga.xml | 304 ++++++++++++++++++
 1 file changed, 304 insertions(+)
 create mode 100644 openfpga_flow/openfpga_arch/k4_frac_N4_adder_chain_mem1K_frac_dsp32_40nm_frame_openfpga.xml

diff --git a/openfpga_flow/openfpga_arch/k4_frac_N4_adder_chain_mem1K_frac_dsp32_40nm_frame_openfpga.xml b/openfpga_flow/openfpga_arch/k4_frac_N4_adder_chain_mem1K_frac_dsp32_40nm_frame_openfpga.xml
new file mode 100644
index 000000000..eb5e3c659
--- /dev/null
+++ b/openfpga_flow/openfpga_arch/k4_frac_N4_adder_chain_mem1K_frac_dsp32_40nm_frame_openfpga.xml
@@ -0,0 +1,304 @@
+<!-- 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" 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_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="static_dff" prefix="dff" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/SpiceNetlists/ff.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/VerilogNetlists/ff.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" size="1" is_global="true" default_val="0" is_set="true"/>
+       <port type="input" prefix="reset" size="1" is_global="true" default_val="0" is_reset="true"/>
+       <port type="output" prefix="Q" size="1"/>
+       <port type="clock" prefix="clk" size="1" is_global="true" 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="config_latch" default_val="1"/>
+    </circuit_model>
+    <!--Scan-chain DFF subckt ports should be defined as <D> <Q> <Qb> <CLK> <RESET> <SET>  -->
+    <circuit_model type="sram" name="config_latch" prefix="config_latch" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/SpiceNetlists/config_latch.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/VerilogNetlists/config_latch.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="reset" size="1" is_global="true" default_val="0" is_reset="true" is_prog="true"/>
+       <port type="bl" prefix="bl" size="1"/>
+       <port type="wl" prefix="wl" size="1"/>
+       <port type="output" prefix="Q" size="1"/>
+       <port type="output" prefix="Qb" size="1"/>
+       <port type="clock" prefix="prog_clk" lib_name="clk" size="1" is_global="true" default_val="0" is_prog="true"/>
+    </circuit_model>
+    <circuit_model type="iopad" name="iopad" prefix="iopad" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/SpiceNetlists/io.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/VerilogNetlists/io.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"/>
+      <port type="sram" prefix="en" size="1" mode_select="true" circuit_model_name="config_latch" default_val="1"/>
+      <port type="input" prefix="outpad" size="1"/>
+      <port type="output" prefix="inpad" size="1"/>
+    </circuit_model>
+    <circuit_model type="hard_logic" name="adder" prefix="adder" is_default="true" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/SpiceNetlists/adder.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/VerilogNetlists/adder.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="a" size="1"/>
+      <port type="input" prefix="b" size="1"/>
+      <port type="input" prefix="cin" size="1"/>
+      <port type="output" prefix="sumout" size="1"/>
+      <port type="output" prefix="cout" size="1"/>
+    </circuit_model>
+    <circuit_model type="hard_logic" name="dpram_128x8" prefix="dpram_128x8" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/SpiceNetlists/dpram.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/VerilogNetlists/dpram1k.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="waddr" size="7"/>
+      <port type="input" prefix="raddr" size="7"/>
+      <port type="input" prefix="d_in" size="8"/>
+      <port type="input" prefix="wen" size="1"/>
+      <port type="input" prefix="ren" size="1"/>
+      <port type="output" prefix="d_out" size="8"/>
+      <port type="clock" prefix="clk" size="1" is_global="true" default_val="0"/>
+    </circuit_model>
+    <circuit_model type="hard_logic" name="mult_32x32" prefix="mult_32x32" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/SpiceNetlists/mult_32x32.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/VerilogNetlists/mult_32x32.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="a" size="32"/>
+      <port type="input" prefix="b" size="32"/>
+      <port type="output" prefix="out" size="64"/>
+      <!-- As a fracturable multiplier, it requires 2 configuration bits to operate in 4 different modes -->
+      <port type="sram" prefix="mode" size="2" mode_select="true" circuit_model_name="config_latch" default_val="1"/>
+    </circuit_model>
+  </circuit_library>
+  <configuration_protocol>
+    <organization type="frame_based" circuit_model_name="config_latch"/>
+  </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>
+  <direct_connection>
+    <direct name="adder_carry" circuit_model_name="direct_interc" type="column" x_dir="positive" y_dir="positive"/>
+  </direct_connection>
+  <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="iopad" 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="static_dff"/>
+    <pb_type name="clb.fle[physical].fabric.adder" circuit_model_name="adder"/>
+    <!-- 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" physical_pb_type_name="clb.fle[physical].fabric.ff"/>
+    <!-- Binding operating pb_types in mode 'arithmetic' -->
+    <pb_type name="clb.fle[arithmetic].arithmetic.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 lut4 to the first 3 inputs of fracturable lut6 -->
+      <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[arithmetic].arithmetic.adder" physical_pb_type_name="clb.fle[physical].fabric.adder"/>
+    <pb_type name="clb.fle[arithmetic].arithmetic.ff" physical_pb_type_name="clb.fle[physical].fabric.ff"/>
+    <!-- Binding operating pb_types in mode 'ble4' -->
+    <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" physical_pb_type_name="clb.fle[physical].fabric.ff" physical_pb_type_index_factor="2" physical_pb_type_index_offset="0"/>
+    <!-- End physical pb_type binding in complex block IO -->
+    <!-- physical pb_type binding in complex block memory -->
+    <pb_type name="memory[mem_128x8_dp].mem_128x8_dp" circuit_model_name="dpram_128x8"/>
+    <!-- END physical pb_type binding in complex block memory -->
+
+    <!-- physical pb_type binding in complex block dsp -->
+    <pb_type name="mult_32" physical_mode_name="mult_32x32" idle_mode_name="mult_32x32"/>
+    <!-- Bind the primitive pb_type in the physical mode to a circuit model --> 
+    <pb_type name="mult_32[mult_32x32].mult_32x32_slice.mult_32x32" circuit_model_name="mult_32x32" mode_bits="00"/>
+    <!-- Bind the 8x8 multiplier to the physical 32x32 multiplier
+         There are four 8x8 multipliers, each of which occupies part
+         of the input/output of the 32x32 multiplier
+      -->
+    <pb_type name="mult_32[two_divisible_mult_16x16].divisible_mult_16x16[two_mult_8x8].mult_8x8_slice.mult_8x8" physical_pb_type_name="mult_32[mult_32x32].mult_32x32_slice.mult_32x32" mode_bits="01" physical_pb_type_index_factor="0">
+      <port name="a" physical_mode_port="a[0:7]" physical_mode_pin_rotate_offset="8"/>
+      <port name="b" physical_mode_port="b[0:7]" physical_mode_pin_rotate_offset="8"/>
+      <port name="out" physical_mode_port="out[0:15]" physical_mode_pin_rotate_offset="16"/>
+    </pb_type>
+    <!-- Bind the 16x16 multiplier to the physical 32x32 multiplier
+         There are two 16x16 multipliers, each of which occupies part
+         of the input/output of the 32x32 multiplier
+      -->
+    <pb_type name="mult_32[two_divisible_mult_16x16].divisible_mult_16x16[mult_16x16].mult_16x16_slice.mult_16x16" physical_pb_type_name="mult_32[mult_32x32].mult_32x32_slice.mult_32x32" mode_bits="10" physical_pb_type_index_factor="0">
+      <port name="a" physical_mode_port="a[0:15]" physical_mode_pin_rotate_offset="16"/>
+      <port name="b" physical_mode_port="b[0:15]" physical_mode_pin_rotate_offset="16"/>
+      <port name="out" physical_mode_port="out[0:31]" physical_mode_pin_rotate_offset="32"/>
+    </pb_type>
+    <!-- END physical pb_type binding in complex block dsp -->
+  </pb_type_annotations>
+</openfpga_architecture>