Merge pull request #249 from lnis-uofu/dev

Reorganize QuickLogic's Regression Tests
This commit is contained in:
tangxifan 2021-02-23 08:35:27 -07:00 committed by GitHub
commit 154f3b6cfc
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
20 changed files with 2893 additions and 32 deletions

View File

@ -1,10 +0,0 @@
IN0 0.505000 0.204400
IN1 0.491000 0.206000
IN2 0.472000 0.204400
clk 0.500000 2.000000
OUT1 0.491000 0.206000
OUT0 0.505000 0.204400
OUT2 0.472000 0.204400
n15 0.491000 0.101146
n18 0.505000 0.103222
n21 0.472000 0.096477

View File

@ -1,19 +0,0 @@
module routing_test(IN0,IN1,IN2, clk, OUT0,OUT1,OUT2);
input wire IN0,IN1,IN2,clk;
output reg OUT0, OUT1, OUT2;
always @(posedge clk)
begin
OUT0 <= IN0;
OUT1 <= IN1;
OUT2 <= IN2;
end
endmodule

View File

@ -0,0 +1,198 @@
<!-- 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
- 8 operating clocks
-->
<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_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>
<global_port name="clk" is_clock="true" default_val="0">
<!-- MUST explicitly define the number of clock bits
being consistent with physical tile port definition
-->
<tile name="clb" port="clk[0:7]" 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[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_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>

View File

@ -0,0 +1,448 @@
<!-- 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="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="frac_lut6" prefix="frac_lut6" 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="-1-1-"/>
<pass_gate_logic circuit_model_name="TGATE"/>
<port type="input" prefix="in" size="6" tri_state_map="----11" circuit_model_name="OR2"/>
<port type="output" prefix="lut4_out" size="4" lut_frac_level="4" lut_output_mask="0,1,2,3"/>
<port type="output" prefix="lut5_out" size="2" lut_frac_level="5" lut_output_mask="0,1"/>
<port type="output" prefix="lut6_out" size="1" lut_output_mask="0"/>
<port type="sram" prefix="sram" size="64"/>
<port type="sram" prefix="mode" size="2" 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_model type="hard_logic" name="ADDF" prefix="ADDF" is_default="true" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/openfpga_cell_library/spice/adder.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/openfpga_cell_library/verilog/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" lib_name="A" size="1"/>
<port type="input" prefix="b" lib_name="B" size="1"/>
<port type="input" prefix="cin" lib_name="CI" size="1"/>
<port type="output" prefix="sumout" lib_name="SUM" size="1"/>
<port type="output" prefix="cout" lib_name="CO" size="1"/>
</circuit_model>
<circuit_model type="hard_logic" name="mult_36x36" prefix="mult_36x36" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/openfpga_cell_library/spice/mult_36x36.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/openfpga_cell_library/verilog/mult_36x36.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" lib_name="A" size="36"/>
<port type="input" prefix="b" lib_name="B" size="36"/>
<port type="output" prefix="out" size="72"/>
<!-- 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="DFFR" default_val="1"/>
</circuit_model>
<circuit_model type="hard_logic" name="frac_mem_32k" prefix="frac_mem_32k" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/openfpga_cell_library/spice/frac_mem_32k.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/openfpga_cell_library/verilog/frac_mem_32k.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="addr1" lib_name="addr_a" size="15"/>
<port type="input" prefix="addr2" lib_name="addr_b" size="15"/>
<port type="input" prefix="data1" lib_name="data_a" size="32"/>
<port type="input" prefix="data2" lib_name="data_b" size="32"/>
<port type="input" prefix="we1" lib_name="we_a" size="1"/>
<port type="input" prefix="we2" lib_name="we_b" size="1"/>
<port type="output" prefix="out1" lib_name="q_a" size="32"/>
<port type="output" prefix="out2" lib_name="q_b" size="32"/>
<port type="clock" prefix="clk" size="1" is_global="false" default_val="0"/>
<!-- As a fracturable memory, it requires 4 configuration bits to operate in 13 different modes -->
<port type="sram" prefix="mode" size="4" mode_select="true" circuit_model_name="DFFR" default_val="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>
<direct_connection>
<direct name="adder_carry" circuit_model_name="direct_interc" type="column" x_dir="positive" y_dir="positive"/>
</direct_connection>
<tile_annotations>
<global_port name="clk" is_clock="true" default_val="0">
<!-- MUST explicitly define the number of clock bits
being consistent with physical tile port definition
-->
<tile name="clb" port="clk[0:7]" x="-1" y="-1"/>
<tile name="memory" port="clk[0:7]" 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[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_lut6" circuit_model_name="frac_lut6" mode_bits="11"/>
<pb_type name="clb.fle[physical].fabric.ff" circuit_model_name="DFFSRQ"/>
<pb_type name="clb.fle[physical].fabric.adder" circuit_model_name="ADDF"/>
<!-- Binding operating pb_type to physical pb_type -->
<!-- Binding operating pb_types in mode 'n2_lut5' -->
<pb_type name="clb.fle[n2_lut5].ble5.lut5" physical_pb_type_name="clb.fle[physical].fabric.frac_logic.frac_lut6" mode_bits="01" physical_pb_type_index_factor="0.5">
<!-- Binding the lut5 to the first 5 inputs of fracturable lut6 -->
<port name="in" physical_mode_port="in[0:4]"/>
<port name="out" physical_mode_port="lut5_out[0:0]" physical_mode_pin_rotate_offset="1"/>
</pb_type>
<pb_type name="clb.fle[n2_lut5].ble5.ff" physical_pb_type_name="clb.fle[physical].fabric.ff"/>
<!-- Binding operating pb_types in mode 'arithmetic' -->
<pb_type name="clb.fle[arithmetic].arithmetic.lut4" physical_pb_type_name="clb.fle[physical].fabric.frac_logic.frac_lut6" mode_bits="11" physical_pb_type_index_factor="0.25">
<!-- Binding the lut4 to the first 4 inputs of fracturable lut6 -->
<port name="in" physical_mode_port="in[0:3]"/>
<port name="out" physical_mode_port="lut4_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 'ble6' -->
<pb_type name="clb.fle[n1_lut6].ble6.lut6" physical_pb_type_name="clb.fle[physical].fabric.frac_logic.frac_lut6" mode_bits="00">
<!-- Binding the lut6 to the first 6 inputs of fracturable lut6 -->
<port name="in" physical_mode_port="in[0:5]"/>
<port name="out" physical_mode_port="lut6_out"/>
</pb_type>
<pb_type name="clb.fle[n1_lut6].ble6.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 clb -->
<!-- physical pb_type binding in complex block dsp -->
<pb_type name="mult_36" physical_mode_name="mult_36x36" idle_mode_name="mult_36x36"/>
<!-- Bind the primitive pb_type in the physical mode to a circuit model -->
<pb_type name="mult_36[mult_36x36].mult_36x36_slice.mult_36x36" circuit_model_name="mult_36x36" mode_bits="00"/>
<!-- Bind the 9x9 multiplier to the physical 36x36 multiplier
There are four 9x9 multipliers, each of which occupies part
of the input/output of the 36x36 multiplier
-->
<pb_type name="mult_36[two_divisible_mult_18x18].divisible_mult_18x18[two_mult_9x9].mult_9x9_slice.mult_9x9" physical_pb_type_name="mult_36[mult_36x36].mult_36x36_slice.mult_36x36" mode_bits="01" physical_pb_type_index_factor="0">
<port name="a" physical_mode_port="a[0:8]" physical_mode_pin_rotate_offset="9"/>
<port name="b" physical_mode_port="b[0:8]" physical_mode_pin_rotate_offset="9"/>
<port name="out" physical_mode_port="out[0:17]" physical_mode_pin_rotate_offset="18"/>
</pb_type>
<!-- Bind the 18x18 multiplier to the physical 36x36 multiplier
There are two 18x18 multipliers, each of which occupies part
of the input/output of the 36x36 multiplier
-->
<pb_type name="mult_36[two_divisible_mult_18x18].divisible_mult_18x18[mult_18x18].mult_18x18_slice.mult_18x18" physical_pb_type_name="mult_36[mult_36x36].mult_36x36_slice.mult_36x36" mode_bits="10" physical_pb_type_index_factor="0">
<port name="a" physical_mode_port="a[0:17]" physical_mode_pin_rotate_offset="18"/>
<port name="b" physical_mode_port="b[0:17]" physical_mode_pin_rotate_offset="18"/>
<port name="out" physical_mode_port="out[0:35]" physical_mode_pin_rotate_offset="36"/>
</pb_type>
<!-- END physical pb_type binding in complex block dsp -->
<!-- physical pb_type binding in complex block memory -->
<pb_type name="memory" physical_mode_name="physical" idle_mode_name="physical"/>
<pb_type name="memory[physical].frac_mem_32k" circuit_model_name="frac_mem_32k" mode_bits="0000"/>
<!-- Bind the 512x64 single port RAM to the physical implementation -->
<pb_type name="memory[mem_512x64_sp].mem_512x64_sp" physical_pb_type_name="memory[physical].frac_mem_32k" mode_bits="0000">
<port name="addr" physical_mode_port="addr1[0:8]"/>
<port name="data" physical_mode_port="data1 data2" physical_mode_pin_initial_offset="0 -32"/>
<port name="we" physical_mode_port="we1"/>
<port name="out" physical_mode_port="out1 out2" physical_mode_pin_initial_offset="0 -32"/>
<port name="clk" physical_mode_port="clk"/>
</pb_type>
<!-- Bind the 1024x32 single port RAM to the physical implementation -->
<pb_type name="memory[mem_1024x32_sp].mem_1024x32_sp" physical_pb_type_name="memory[physical].frac_mem_32k" mode_bits="0001">
<port name="addr" physical_mode_port="addr1[0:9]"/>
<port name="data" physical_mode_port="data1"/>
<port name="we" physical_mode_port="we1"/>
<port name="out" physical_mode_port="out1"/>
<port name="clk" physical_mode_port="clk"/>
</pb_type>
<!-- Bind the 2048x16 single port RAM to the physical implementation -->
<pb_type name="memory[mem_2048x16_sp].mem_2048x16_sp" physical_pb_type_name="memory[physical].frac_mem_32k" mode_bits="0010">
<port name="addr" physical_mode_port="addr1[0:10]"/>
<port name="data" physical_mode_port="data1[0:15]"/>
<port name="we" physical_mode_port="we1"/>
<port name="out" physical_mode_port="out1[0:15]"/>
<port name="clk" physical_mode_port="clk"/>
</pb_type>
<!-- Bind the 4096x8 single port RAM to the physical implementation -->
<pb_type name="memory[mem_4096x8_sp].mem_4096x8_sp" physical_pb_type_name="memory[physical].frac_mem_32k" mode_bits="0011">
<port name="addr" physical_mode_port="addr1[0:11]"/>
<port name="data" physical_mode_port="data1[0:7]"/>
<port name="we" physical_mode_port="we1"/>
<port name="out" physical_mode_port="out1[0:7]"/>
<port name="clk" physical_mode_port="clk"/>
</pb_type>
<!-- Bind the 8192x4 single port RAM to the physical implementation -->
<pb_type name="memory[mem_8192x4_sp].mem_8192x4_sp" physical_pb_type_name="memory[physical].frac_mem_32k" mode_bits="0100">
<port name="addr" physical_mode_port="addr1[0:12]"/>
<port name="data" physical_mode_port="data1[0:3]"/>
<port name="we" physical_mode_port="we1"/>
<port name="out" physical_mode_port="out1[0:3]"/>
<port name="clk" physical_mode_port="clk"/>
</pb_type>
<!-- Bind the 16384x2 single port RAM to the physical implementation -->
<pb_type name="memory[mem_16384x2_sp].mem_16384x2_sp" physical_pb_type_name="memory[physical].frac_mem_32k" mode_bits="0101">
<port name="addr" physical_mode_port="addr1[0:13]"/>
<port name="data" physical_mode_port="data1[0:1]"/>
<port name="we" physical_mode_port="we1"/>
<port name="out" physical_mode_port="out1[0:1]"/>
<port name="clk" physical_mode_port="clk"/>
</pb_type>
<!-- Bind the 32768x1 single port RAM to the physical implementation -->
<pb_type name="memory[mem_32768x1_sp].mem_32768x1_sp" physical_pb_type_name="memory[physical].frac_mem_32k" mode_bits="0110">
<port name="addr" physical_mode_port="addr1[0:14]"/>
<port name="data" physical_mode_port="data1[0:0]"/>
<port name="we" physical_mode_port="we1"/>
<port name="out" physical_mode_port="out1[0:0]"/>
<port name="clk" physical_mode_port="clk"/>
</pb_type>
<!-- Bind the 1024x32 dual port RAM to the physical implementation -->
<pb_type name="memory[mem_1024x32_dp].mem_1024x32_dp" physical_pb_type_name="memory[physical].frac_mem_32k" mode_bits="0111">
<port name="addr1" physical_mode_port="addr1[0:9]"/>
<port name="addr2" physical_mode_port="addr2[0:9]"/>
<port name="data1" physical_mode_port="data1[0:31]"/>
<port name="data2" physical_mode_port="data2[0:31]"/>
<port name="we1" physical_mode_port="we1"/>
<port name="we2" physical_mode_port="we2"/>
<port name="out1" physical_mode_port="out1[0:31]"/>
<port name="out2" physical_mode_port="out2[0:31]"/>
<port name="clk" physical_mode_port="clk"/>
</pb_type>
<!-- Bind the 2048x16 dual port RAM to the physical implementation -->
<pb_type name="memory[mem_2048x16_dp].mem_2048x16_dp" physical_pb_type_name="memory[physical].frac_mem_32k" mode_bits="1000">
<port name="addr1" physical_mode_port="addr1[0:10]"/>
<port name="addr2" physical_mode_port="addr2[0:10]"/>
<port name="data1" physical_mode_port="data1[0:15]"/>
<port name="data2" physical_mode_port="data2[0:15]"/>
<port name="we1" physical_mode_port="we1"/>
<port name="we2" physical_mode_port="we2"/>
<port name="out1" physical_mode_port="out1[0:15]"/>
<port name="out2" physical_mode_port="out2[0:15]"/>
<port name="clk" physical_mode_port="clk"/>
</pb_type>
<!-- Bind the 4096x8 dual port RAM to the physical implementation -->
<pb_type name="memory[mem_4096x8_dp].mem_4096x8_dp" physical_pb_type_name="memory[physical].frac_mem_32k" mode_bits="1001">
<port name="addr1" physical_mode_port="addr1[0:11]"/>
<port name="addr2" physical_mode_port="addr2[0:11]"/>
<port name="data1" physical_mode_port="data1[0:7]"/>
<port name="data2" physical_mode_port="data2[0:7]"/>
<port name="we1" physical_mode_port="we1"/>
<port name="we2" physical_mode_port="we2"/>
<port name="out1" physical_mode_port="out1[0:7]"/>
<port name="out2" physical_mode_port="out2[0:7]"/>
<port name="clk" physical_mode_port="clk"/>
</pb_type>
<!-- Bind the 8192x4 dual port RAM to the physical implementation -->
<pb_type name="memory[mem_8192x4_dp].mem_8192x4_dp" physical_pb_type_name="memory[physical].frac_mem_32k" mode_bits="1010">
<port name="addr1" physical_mode_port="addr1[0:12]"/>
<port name="addr2" physical_mode_port="addr2[0:12]"/>
<port name="data1" physical_mode_port="data1[0:3]"/>
<port name="data2" physical_mode_port="data2[0:3]"/>
<port name="we1" physical_mode_port="we1"/>
<port name="we2" physical_mode_port="we2"/>
<port name="out1" physical_mode_port="out1[0:3]"/>
<port name="out2" physical_mode_port="out2[0:3]"/>
<port name="clk" physical_mode_port="clk"/>
</pb_type>
<!-- Bind the 16384x2 dual port RAM to the physical implementation -->
<pb_type name="memory[mem_16384x2_dp].mem_16384x2_dp" physical_pb_type_name="memory[physical].frac_mem_32k" mode_bits="1011">
<port name="addr1" physical_mode_port="addr1[0:13]"/>
<port name="addr2" physical_mode_port="addr2[0:13]"/>
<port name="data1" physical_mode_port="data1[0:1]"/>
<port name="data2" physical_mode_port="data2[0:1]"/>
<port name="we1" physical_mode_port="we1"/>
<port name="we2" physical_mode_port="we2"/>
<port name="out1" physical_mode_port="out1[0:1]"/>
<port name="out2" physical_mode_port="out2[0:1]"/>
<port name="clk" physical_mode_port="clk"/>
</pb_type>
<!-- Bind the 32768x1 dual port RAM to the physical implementation -->
<pb_type name="memory[mem_32768x1_dp].mem_32768x1_dp" physical_pb_type_name="memory[physical].frac_mem_32k" mode_bits="1100">
<port name="addr1" physical_mode_port="addr1[0:14]"/>
<port name="addr2" physical_mode_port="addr2[0:14]"/>
<port name="data1" physical_mode_port="data1[0:0]"/>
<port name="data2" physical_mode_port="data2[0:0]"/>
<port name="we1" physical_mode_port="we1"/>
<port name="we2" physical_mode_port="we2"/>
<port name="out1" physical_mode_port="out1[0:0]"/>
<port name="out2" physical_mode_port="out2[0:0]"/>
<port name="clk" physical_mode_port="clk"/>
</pb_type>
<!-- END physical pb_type binding in complex block memory -->
</pb_type_annotations>
</openfpga_architecture>

View File

@ -0,0 +1,61 @@
# 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}
# 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
# Note: no need to assign activity file when you used a fixed number
# of clock cycles in simulation settings
# Also, ACE2 does not support multiple clocks
# Therefore, activity file is not recommended for multi-clock fabric/implementations
link_openfpga_arch --sort_gsb_chan_node_in_edges
# Check and correct any naming conflicts in the BLIF netlist
check_netlist_naming_conflict --fix --report ./netlist_renaming.xml
# Apply fix-up to clustering nets based on routing results
pb_pin_fixup --verbose
# Apply fix-up to Look-Up Table truth tables based on packing results
lut_truth_table_fixup
# Build the module graph
# - Enabled compression on routing architecture modules
# - Enable pin duplication on grid modules
# - Enabled frame view creation to save runtime and memory
# Note that this is turned on when bitstream generation
# is the ONLY purpose of the flow!!!
build_fabric --compress_routing --frame_view #--verbose
# 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 --design_constraints ${OPENFPGA_REPACK_DESIGN_CONSTRAINTS_FILE} #--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.xml --format xml
# Finish and exit OpenFPGA
exit
# Note :
# To run verification at the end of the flow maintain source in ./SRC directory

View File

@ -0,0 +1,61 @@
# 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} --route_chan_width ${OPENFPGA_VPR_ROUTE_CHAN_WIDTH} --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
# Note: no need to assign activity file when you used a fixed number
# of clock cycles in simulation settings
# Also, ACE2 does not support multiple clocks
# Therefore, activity file is not recommended for multi-clock fabric/implementations
link_openfpga_arch --sort_gsb_chan_node_in_edges
# Check and correct any naming conflicts in the BLIF netlist
check_netlist_naming_conflict --fix --report ./netlist_renaming.xml
# Apply fix-up to clustering nets based on routing results
pb_pin_fixup --verbose
# Apply fix-up to Look-Up Table truth tables based on packing results
lut_truth_table_fixup
# Build the module graph
# - Enabled compression on routing architecture modules
# - Enable pin duplication on grid modules
# - Enabled frame view creation to save runtime and memory
# Note that this is turned on when bitstream generation
# is the ONLY purpose of the flow!!!
build_fabric --compress_routing --frame_view #--verbose
# 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 --design_constraints ${OPENFPGA_REPACK_DESIGN_CONSTRAINTS_FILE} #--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.xml --format xml
# Finish and exit OpenFPGA
exit
# Note :
# To run verification at the end of the flow maintain source in ./SRC directory

View File

@ -12,6 +12,10 @@
Note that Note that
- clock name must be unique as it is used in testbench genertion - clock name must be unique as it is used in testbench genertion
- the clock port must match clock port definition in OpenFPGA architecture XML!!! - the clock port must match clock port definition in OpenFPGA architecture XML!!!
Note: This clock setting is also applicable to architectures with 4+ clocks
In that case, the first 4-bit of the clock port will be driven by different clock frequencies
while the rest bits of the clock port will be driven by the default clock frequency
--> -->
<operating frequency="50e6" num_cycles="20" slack="0.2"> <operating frequency="50e6" num_cycles="20" slack="0.2">
<clock name="clk_10MHz" port="clk[0:0]" frequency="10e6"/> <clock name="clk_10MHz" port="clk[0:0]" frequency="10e6"/>

View File

@ -0,0 +1,59 @@
<!-- Simulation Setting for OpenFPGA framework
This file will use automatic inference for any settings
including:
- auto select the number of simulation cycles
- auto select the simulation clock frequency from VPR results
-->
<openfpga_simulation_setting>
<clock_setting>
<!-- The frequency defined in the operating line will be
the default operating clock frequency for all the clocks
define specific frequency using <clock> line will overwrite the default value
Note that
- clock name must be unique as it is used in testbench genertion
- the clock port must match clock port definition in OpenFPGA architecture XML!!!
Note: This clock setting is also applicable to architectures with 8+ clocks
In that case, the first 8-bit of the clock port will be driven by different clock frequencies
while the rest bits of the clock port will be driven by the default clock frequency
-->
<operating frequency="50e6" num_cycles="20" slack="0.2">
<clock name="clk_10MHz" port="clk[0:0]" frequency="10e6"/>
<clock name="clk_20MHz" port="clk[1:1]" frequency="20e6"/>
<clock name="clk_30MHz" port="clk[2:2]" frequency="30e6"/>
<clock name="clk_40MHz" port="clk[3:3]" frequency="40e6"/>
<clock name="clk_50MHz" port="clk[4:4]" frequency="50e6"/>
<clock name="clk_60MHz" port="clk[5:5]" frequency="60e6"/>
<clock name="clk_70MHz" port="clk[6:6]" frequency="70e6"/>
<clock name="clk_80MHz" port="clk[7:7]" frequency="80e6"/>
</operating>
<programming frequency="100e6"/>
</clock_setting>
<simulator_option>
<operating_condition temperature="25"/>
<output_log verbose="false" captab="false"/>
<accuracy type="abs" value="1e-13"/>
<runtime fast_simulation="true"/>
</simulator_option>
<monte_carlo num_simulation_points="2"/>
<measurement_setting>
<slew>
<rise upper_thres_pct="0.95" lower_thres_pct="0.05"/>
<fall upper_thres_pct="0.05" lower_thres_pct="0.95"/>
</slew>
<delay>
<rise input_thres_pct="0.5" output_thres_pct="0.5"/>
<fall input_thres_pct="0.5" output_thres_pct="0.5"/>
</delay>
</measurement_setting>
<stimulus>
<clock>
<rise slew_type="abs" slew_time="20e-12" />
<fall slew_type="abs" slew_time="20e-12" />
</clock>
<input>
<rise slew_type="abs" slew_time="25e-12" />
<fall slew_type="abs" slew_time="25e-12" />
</input>
</stimulus>
</openfpga_simulation_setting>

View File

@ -10,3 +10,7 @@ echo -e "QuickLogic regression tests";
echo -e "Testing yosys flow using custom ys script for running quicklogic device"; echo -e "Testing yosys flow using custom ys script for running quicklogic device";
run-task quicklogic_tests/flow_test --debug --show_thread_logs run-task quicklogic_tests/flow_test --debug --show_thread_logs
echo -e "Testing yosys flow using custom ys script for running multi-clock quicklogic device";
run-task quicklogic_tests/counter_5clock_test --debug --show_thread_logs
run-task quicklogic_tests/sdc_controller_test --debug --show_thread_logs

View File

@ -19,5 +19,8 @@ The principle is that each OpenFPGA tool should have a set of regression tests.
- FPGA-SPICE regression test should focus on SPICE netlist generation / compilation and SPICE simulations qwith QoR checks. - FPGA-SPICE regression test should focus on SPICE netlist generation / compilation and SPICE simulations qwith QoR checks.
- Quicklogic regression test is to ensure working flows for QuickLogic's devices and variants
- Benchmark sweep regression test should focus on testing mainly the bitstream generation for a wide range of benchmark suites
Please keep this README up-to-date on the OpenFPGA tools Please keep this README up-to-date on the OpenFPGA tools

View File

@ -0,0 +1,12 @@
<pin_constraints>
<!-- For a given .blif file, we want to assign
- the clk0 signal to the clk[0] port of the FPGA fabric
- the clk1 signal to the clk[1] port of the FPGA fabric
-->
<set_io pin="clk[0]" net="clk1"/>
<set_io pin="clk[1]" net="clk2"/>
<set_io pin="clk[2]" net="clk3"/>
<set_io pin="clk[3]" net="clk4"/>
<set_io pin="clk[4]" net="clk5"/>
</pin_constraints>

View File

@ -0,0 +1,18 @@
<repack_design_constraints>
<!-- For a given .blif file, we want to assign
- the clk0 signal to the clk[0] port of all the clb tiles available in the FPGA fabric
- the clk1 signal to the clk[1] port of all the clb tiles available in the FPGA fabric
and ensure no signals could be mapped to
- the clk[2] port of all the clb tiles available in the FPGA fabric
- the clk[3] port of all the clb tiles available in the FPGA fabric
-->
<pin_constraint pb_type="clb" pin="clk[0]" net="clk1"/>
<pin_constraint pb_type="clb" pin="clk[1]" net="clk2"/>
<pin_constraint pb_type="clb" pin="clk[2]" net="clk3"/>
<pin_constraint pb_type="clb" pin="clk[3]" net="clk4"/>
<pin_constraint pb_type="clb" pin="clk[4]" net="clk5"/>
<pin_constraint pb_type="clb" pin="clk[5]" net="OPEN"/>
<pin_constraint pb_type="clb" pin="clk[6]" net="OPEN"/>
<pin_constraint pb_type="clb" pin="clk[7]" net="OPEN"/>
</repack_design_constraints>

View File

@ -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 = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
power_analysis = false
spice_output=false
verilog_output=true
timeout_each_job = 1*60
fpga_flow=yosys_vpr
[OpenFPGA_SHELL]
openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_shell_scripts/generate_bitstream_global_tile_multiclock_example_script.openfpga
openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k4_N4_40nm_GlobalTile8Clk_cc_openfpga.xml
openfpga_sim_setting_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_simulation_settings/fixed_8clock_sim_openfpga.xml
openfpga_repack_design_constraints_file=${PATH:OPENFPGA_PATH}/openfpga_flow/tasks/quicklogic_tests/counter_5clock_test/config/repack_pin_constraints.xml
openfpga_pin_constraints_file=${PATH:OPENFPGA_PATH}/openfpga_flow/tasks/quicklogic_tests/counter_5clock_test/config/pin_constraints.xml
[ARCHITECTURES]
arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/vpr_arch/k4_N4_tileable_GlobalTile8Clk_40nm.xml
[BENCHMARKS]
bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/quicklogic_tests/counter120bitx5/rtl/*.v
[SYNTHESIS_PARAM]
bench0_top = counter120bitx5
bench0_yosys=${PATH:OPENFPGA_PATH}/openfpga_flow/misc/quicklogic_yosys_flow_ap3.ys
[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]

View File

@ -28,7 +28,6 @@ bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/quicklogic_tests/io_tc1/rt
bench1=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/quicklogic_tests/unsigned_mult_80/rtl/*.v bench1=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/quicklogic_tests/unsigned_mult_80/rtl/*.v
bench2=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/quicklogic_tests/bin2bcd/bin2bcd.v bench2=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/quicklogic_tests/bin2bcd/bin2bcd.v
bench3=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/quicklogic_tests/counter/counter.v bench3=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/quicklogic_tests/counter/counter.v
bench4=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/quicklogic_tests/routing_test/routing_test.v
bench5=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/quicklogic_tests/rs_decoder/rtl/rs_decoder.v bench5=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/quicklogic_tests/rs_decoder/rtl/rs_decoder.v
bench6=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/quicklogic_tests/simon_bit_serial/rtl/*.v bench6=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/quicklogic_tests/simon_bit_serial/rtl/*.v
bench7=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/quicklogic_tests/sha256/rtl/*.v bench7=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/quicklogic_tests/sha256/rtl/*.v
@ -56,8 +55,6 @@ bench2_top = bin2bcd
bench2_yosys=${PATH:OPENFPGA_PATH}/openfpga_flow/misc/quicklogic_yosys_flow_ap3.ys bench2_yosys=${PATH:OPENFPGA_PATH}/openfpga_flow/misc/quicklogic_yosys_flow_ap3.ys
bench3_top = counter bench3_top = counter
bench3_yosys=${PATH:OPENFPGA_PATH}/openfpga_flow/misc/quicklogic_yosys_flow_ap3.ys bench3_yosys=${PATH:OPENFPGA_PATH}/openfpga_flow/misc/quicklogic_yosys_flow_ap3.ys
bench4_top = routing_test
bench4_yosys=${PATH:OPENFPGA_PATH}/openfpga_flow/misc/quicklogic_yosys_flow_ap3.ys
bench5_top = rs_decoder_top bench5_top = rs_decoder_top
bench5_yosys=${PATH:OPENFPGA_PATH}/openfpga_flow/misc/quicklogic_yosys_flow_ap3.ys bench5_yosys=${PATH:OPENFPGA_PATH}/openfpga_flow/misc/quicklogic_yosys_flow_ap3.ys
bench6_top = top_module bench6_top = top_module

View File

@ -0,0 +1,10 @@
<pin_constraints>
<!-- For a given .blif file, we want to assign
- the clk0 signal to the clk[0] port of the FPGA fabric
- the clk1 signal to the clk[1] port of the FPGA fabric
-->
<set_io pin="clk[0]" net="wb_clk_i"/>
<set_io pin="clk[1]" net="sd_clk_i_pad"/>
<set_io pin="clk[2]" net="sd_clk_o_pad"/>
</pin_constraints>

View File

@ -0,0 +1,18 @@
<repack_design_constraints>
<!-- For a given .blif file, we want to assign
- the clk0 signal to the clk[0] port of all the clb tiles available in the FPGA fabric
- the clk1 signal to the clk[1] port of all the clb tiles available in the FPGA fabric
and ensure no signals could be mapped to
- the clk[2] port of all the clb tiles available in the FPGA fabric
- the clk[3] port of all the clb tiles available in the FPGA fabric
-->
<pin_constraint pb_type="clb" pin="clk[0]" net="wb_clk_i"/>
<pin_constraint pb_type="clb" pin="clk[1]" net="sd_clk_i_pad"/>
<pin_constraint pb_type="clb" pin="clk[2]" net="sd_clk_o_pad"/>
<pin_constraint pb_type="clb" pin="clk[3]" net="OPEN"/>
<pin_constraint pb_type="clb" pin="clk[4]" net="OPEN"/>
<pin_constraint pb_type="clb" pin="clk[5]" net="OPEN"/>
<pin_constraint pb_type="clb" pin="clk[6]" net="OPEN"/>
<pin_constraint pb_type="clb" pin="clk[7]" net="OPEN"/>
</repack_design_constraints>

View File

@ -0,0 +1,43 @@
# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
# 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 = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
power_analysis = false
spice_output=false
verilog_output=true
# Runtime is around 3 minutes
# But it can be efficiently reduced by improving synthesis script
# (See detailed comments in Synthesis parameter section)
timeout_each_job = 5*60
fpga_flow=yosys_vpr
[OpenFPGA_SHELL]
openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_shell_scripts/generate_bitstream_global_tile_multiclock_fix_device_example_script.openfpga
openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k6_frac_N10_adder_chain_frac_mem32K_frac_dsp36_40nm_GlobalTile8Clk_openfpga.xml
openfpga_sim_setting_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_simulation_settings/fixed_8clock_sim_openfpga.xml
openfpga_repack_design_constraints_file=${PATH:OPENFPGA_PATH}/openfpga_flow/tasks/quicklogic_tests/sdc_controller_test/config/repack_pin_constraints.xml
openfpga_pin_constraints_file=${PATH:OPENFPGA_PATH}/openfpga_flow/tasks/quicklogic_tests/sdc_controller_test/config/pin_constraints.xml
openfpga_vpr_route_chan_width=200
openfpga_vpr_device_layout=32x32
[ARCHITECTURES]
arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/vpr_arch/k6_frac_N10_tileable_adder_chain_frac_mem32K_frac_dsp36_GlobalTile8Clk_40nm.xml
[BENCHMARKS]
bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/quicklogic_tests/sdc_controller/rtl/*.v
[SYNTHESIS_PARAM]
bench0_top = sdc_controller
# Use standard script for now because QL synthesis recipe generates $DFF_PP model
# Also current synthesis recipe does not support FIFO, BRAM and multiplier
# which causes runtime to be long
#bench0_yosys=${PATH:OPENFPGA_PATH}/openfpga_flow/misc/quicklogic_yosys_flow_ap3.ys
[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]

View File

@ -0,0 +1,296 @@
<!--
Architecture with no fracturable LUTs
- 40 nm technology
- General purpose logic block:
K = 4, N = 4
- Routing architecture: L = 4, fc_in = 0.15, Fc_out = 0.1
- 8 operating clocks which can be selected for each logic element
Details on Modelling:
Based on flagship k6_frac_N10_mem32K_40nm.xml architecture. This architecture has no fracturable LUTs nor any heterogeneous blocks.
Authors: Jason Luu, Jeff Goeders, Vaughn Betz
-->
<architecture>
<!--
ODIN II specific config begins
Describes the types of user-specified netlist blocks (in blif, this corresponds to
".model [type_of_block]") that this architecture supports.
Note: Basic LUTs, I/Os, and flip-flops are not included here as there are
already special structures in blif (.names, .input, .output, and .latch)
that describe them.
-->
<models>
<!-- A virtual model for I/O to be used in the physical mode of io block -->
<model name="io">
<input_ports>
<port name="outpad"/>
</input_ports>
<output_ports>
<port name="inpad"/>
</output_ports>
</model>
</models>
<tiles>
<tile name="io" capacity="8" area="0">
<equivalent_sites>
<site pb_type="io"/>
</equivalent_sites>
<input name="outpad" num_pins="1"/>
<output name="inpad" num_pins="1"/>
<fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10"/>
<pinlocations pattern="custom">
<loc side="left">io.outpad io.inpad</loc>
<loc side="top">io.outpad io.inpad</loc>
<loc side="right">io.outpad io.inpad</loc>
<loc side="bottom">io.outpad io.inpad</loc>
</pinlocations>
</tile>
<tile name="clb" area="53894">
<equivalent_sites>
<site pb_type="clb"/>
</equivalent_sites>
<input name="I" num_pins="10" equivalent="full"/>
<output name="O" num_pins="4" equivalent="none"/>
<clock name="clk" num_pins="8"/>
<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>
<pinlocations pattern="spread"/>
</tile>
</tiles>
<!-- ODIN II specific config ends -->
<!-- Physical descriptions begin -->
<layout tileable="true">
<auto_layout aspect_ratio="1.0">
<!--Perimeter of 'io' blocks with 'EMPTY' blocks at corners-->
<perimeter type="io" priority="100"/>
<corners type="EMPTY" priority="101"/>
<!--Fill with 'clb'-->
<fill type="clb" priority="10"/>
</auto_layout>
<fixed_layout name="2x2" width="4" height="4">
<!--Perimeter of 'io' blocks with 'EMPTY' blocks at corners-->
<perimeter type="io" priority="100"/>
<corners type="EMPTY" priority="101"/>
<!--Fill with 'clb'-->
<fill type="clb" priority="10"/>
</fixed_layout>
</layout>
<device>
<!-- VB & JL: Using Ian Kuon's transistor sizing and drive strength data for routing, at 40 nm. Ian used BPTM
models. We are modifying the delay values however, to include metal C and R, which allows more architecture
experimentation. We are also modifying the relative resistance of PMOS to be 1.8x that of NMOS
(vs. Ian's 3x) as 1.8x lines up with Jeff G's data from a 45 nm process (and is more typical of
45 nm in general). I'm upping the Rmin_nmos from Ian's just over 6k to nearly 9k, and dropping
RminW_pmos from 18k to 16k to hit this 1.8x ratio, while keeping the delays of buffers approximately
lined up with Stratix IV.
We are using Jeff G.'s capacitance data for 45 nm (in tech/ptm_45nm).
Jeff's tables list C in for transistors with widths in multiples of the minimum feature size (45 nm).
The minimum contactable transistor is 2.5 * 45 nm, so I need to multiply drive strength sizes in this file
by 2.5x when looking up in Jeff's tables.
The delay values are lined up with Stratix IV, which has an architecture similar to this
proposed FPGA, and which is also 40 nm
C_ipin_cblock: input capacitance of a track buffer, which VPR assumes is a single-stage
4x minimum drive strength buffer. -->
<sizing R_minW_nmos="8926" R_minW_pmos="16067"/>
<!-- The grid_logic_tile_area below will be used for all blocks that do not explicitly set their own (non-routing)
area; set to 0 since we explicitly set the area of all blocks currently in this architecture file.
-->
<area grid_logic_tile_area="0"/>
<chan_width_distr>
<x distr="uniform" peak="1.000000"/>
<y distr="uniform" peak="1.000000"/>
</chan_width_distr>
<switch_block type="wilton" fs="3"/>
<connection_block input_switch_name="ipin_cblock"/>
</device>
<switchlist>
<!-- VB: the mux_trans_size and buf_size data below is in minimum width transistor *areas*, assuming the purple
book area formula. This means the mux transistors are about 5x minimum drive strength.
We assume the first stage of the buffer is 3x min drive strength to be reasonable given the large
mux transistors, and this gives a reasonable stage ratio of a bit over 5x to the second stage. We assume
the n and p transistors in the first stage are equal-sized to lower the buffer trip point, since it's fed
by a pass transistor mux. We can then reverse engineer the buffer second stage to hit the specified
buf_size (really buffer area) - 16.2x minimum drive nmos and 1.8*16.2 = 29.2x minimum drive.
I then took the data from Jeff G.'s PTM modeling of 45 nm to get the Cin (gate of first stage) and Cout
(diff of second stage) listed below. Jeff's models are in tech/ptm_45nm, and are in min feature multiples.
The minimum contactable transistor is 2.5 * 45 nm, so I need to multiply the drive strength sizes above by
2.5x when looking up in Jeff's tables.
Finally, we choose a switch delay (58 ps) that leads to length 4 wires having a delay equal to that of SIV of 126 ps.
This also leads to the switch being 46% of the total wire delay, which is reasonable. -->
<switch type="mux" name="0" R="551" Cin=".77e-15" Cout="4e-15" Tdel="58e-12" mux_trans_size="2.630740" buf_size="27.645901"/>
<!--switch ipin_cblock resistance set to yeild for 4x minimum drive strength buffer-->
<switch type="mux" name="ipin_cblock" R="2231.5" Cout="0." Cin="1.47e-15" Tdel="7.247000e-11" mux_trans_size="1.222260" buf_size="auto"/>
</switchlist>
<segmentlist>
<!--- VB & JL: using ITRS metal stack data, 96 nm half pitch wires, which are intermediate metal width/space.
With the 96 nm half pitch, such wires would take 60 um of height, vs. a 90 nm high (approximated as square) Stratix IV tile so this seems
reasonable. Using a tile length of 90 nm, corresponding to the length of a Stratix IV tile if it were square. -->
<segment name="L4" freq="1.000000" length="4" type="unidir" Rmetal="101" Cmetal="22.5e-15">
<mux name="0"/>
<sb type="pattern">1 1 1 1 1</sb>
<cb type="pattern">1 1 1 1</cb>
</segment>
</segmentlist>
<complexblocklist>
<!-- Define I/O pads begin -->
<!-- Capacity is a unique property of I/Os, it is the maximum number of I/Os that can be placed at the same (X,Y) location on the FPGA -->
<!-- Not sure of the area of an I/O (varies widely), and it's not relevant to the design of the FPGA core, so we're setting it to 0. -->
<pb_type name="io">
<input name="outpad" num_pins="1"/>
<output name="inpad" num_pins="1"/>
<!-- A mode denotes the physical implementation of an I/O
This mode will be not packable but is mainly used for fabric verilog generation
-->
<mode name="physical" disable_packing="true">
<pb_type name="iopad" blif_model=".subckt io" num_pb="1">
<input name="outpad" num_pins="1"/>
<output name="inpad" num_pins="1"/>
</pb_type>
<interconnect>
<direct name="outpad" input="io.outpad" output="iopad.outpad">
<delay_constant max="1.394e-11" in_port="io.outpad" out_port="iopad.outpad"/>
</direct>
<direct name="inpad" input="iopad.inpad" output="io.inpad">
<delay_constant max="4.243e-11" in_port="iopad.inpad" out_port="io.inpad"/>
</direct>
</interconnect>
</mode>
<!-- IOs can operate as either inputs or outputs.
Delays below come from Ian Kuon. They are small, so they should be interpreted as
the delays to and from registers in the I/O (and generally I/Os are registered
today and that is when you timing analyze them.
-->
<mode name="inpad">
<pb_type name="inpad" blif_model=".input" num_pb="1">
<output name="inpad" num_pins="1"/>
</pb_type>
<interconnect>
<direct name="inpad" input="inpad.inpad" output="io.inpad">
<delay_constant max="4.243e-11" in_port="inpad.inpad" out_port="io.inpad"/>
</direct>
</interconnect>
</mode>
<mode name="outpad">
<pb_type name="outpad" blif_model=".output" num_pb="1">
<input name="outpad" num_pins="1"/>
</pb_type>
<interconnect>
<direct name="outpad" input="io.outpad" output="outpad.outpad">
<delay_constant max="1.394e-11" in_port="io.outpad" out_port="outpad.outpad"/>
</direct>
</interconnect>
</mode>
<!-- Every input pin is driven by 15% of the tracks in a channel, every output pin is driven by 10% of the tracks in a channel -->
<!-- IOs go on the periphery of the FPGA, for consistency,
make it physically equivalent on all sides so that only one definition of I/Os is needed.
If I do not make a physically equivalent definition, then I need to define 4 different I/Os, one for each side of the FPGA
-->
<!-- Place I/Os on the sides of the FPGA -->
<power method="ignore"/>
</pb_type>
<!-- Define I/O pads ends -->
<!-- Define general purpose logic block (CLB) begin -->
<!--- Area calculation: Total Stratix IV tile area is about 8100 um^2, and a minimum width transistor
area is 60 L^2 yields a tile area of 84375 MWTAs.
Routing at W=300 is 30481 MWTAs, leaving us with a total of 53000 MWTAs for logic block area
This means that only 37% of our area is in the general routing, and 63% is inside the logic
block. Note that the crossbar / local interconnect is considered part of the logic block
area in this analysis. That is a lower proportion of of routing area than most academics
assume, but note that the total routing area really includes the crossbar, which would push
routing area up significantly, we estimate into the ~70% range.
-->
<pb_type name="clb">
<input name="I" num_pins="10" equivalent="full"/>
<output name="O" num_pins="4" equivalent="none"/>
<clock name="clk" num_pins="8"/>
<!-- Describe basic logic element.
Each basic logic element has a 4-LUT that can be optionally registered
-->
<pb_type name="fle" num_pb="4">
<input name="in" num_pins="4"/>
<output name="out" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<!-- 4-LUT mode definition begin -->
<mode name="n1_lut4">
<!-- Define 4-LUT mode -->
<pb_type name="ble4" num_pb="1">
<input name="in" num_pins="4"/>
<output name="out" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<!-- Define LUT -->
<pb_type name="lut4" blif_model=".names" num_pb="1" class="lut">
<input name="in" num_pins="4" port_class="lut_in"/>
<output name="out" num_pins="1" port_class="lut_out"/>
<!-- LUT timing using delay matrix -->
<delay_matrix type="max" in_port="lut4.in" out_port="lut4.out">
261e-12
261e-12
261e-12
261e-12
</delay_matrix>
</pb_type>
<!-- Define flip-flop -->
<pb_type name="ff" blif_model=".latch" num_pb="1" class="flipflop">
<input name="D" num_pins="1" port_class="D"/>
<output name="Q" num_pins="1" port_class="Q"/>
<clock name="clk" num_pins="1" port_class="clock"/>
<T_setup value="66e-12" port="ff.D" clock="clk"/>
<T_clock_to_Q max="124e-12" port="ff.Q" clock="clk"/>
</pb_type>
<interconnect>
<direct name="direct1" input="ble4.in" output="lut4[0:0].in"/>
<direct name="direct2" input="lut4.out" output="ff.D">
<!-- Advanced user option that tells CAD tool to find LUT+FF pairs in netlist -->
<pack_pattern name="ble4" in_port="lut4.out" out_port="ff.D"/>
</direct>
<direct name="direct3" input="ble4.clk" output="ff.clk"/>
<mux name="mux1" input="ff.Q lut4.out" output="ble4.out">
<!-- LUT to output is faster than FF to output on a Stratix IV -->
<delay_constant max="25e-12" in_port="lut4.out" out_port="ble4.out"/>
<delay_constant max="45e-12" in_port="ff.Q" out_port="ble4.out"/>
</mux>
</interconnect>
</pb_type>
<interconnect>
<direct name="direct1" input="fle.in" output="ble4.in"/>
<direct name="direct2" input="ble4.out" output="fle.out[0:0]"/>
<direct name="direct3" input="fle.clk" output="ble4.clk"/>
</interconnect>
</mode>
<!-- 6-LUT mode definition end -->
</pb_type>
<interconnect>
<!-- We use a full crossbar to get logical equivalence at inputs of CLB
The delays below come from Stratix IV. the delay through a connection block
input mux + the crossbar in Stratix IV is 167 ps. We already have a 72 ps
delay on the connection block input mux (modeled by Ian Kuon), so the remaining
delay within the crossbar is 95 ps.
The delays of cluster feedbacks in Stratix IV is 100 ps, when driven by a LUT.
Since all our outputs LUT outputs go to a BLE output, and have a delay of
25 ps to do so, we subtract 25 ps from the 100 ps delay of a feedback
to get the part that should be marked on the crossbar. -->
<complete name="crossbar" input="clb.I fle[3:0].out" output="fle[3:0].in">
<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" output="fle[3:0].clk">
</complete>
<!-- This way of specifying direct connection to clb outputs is important because this architecture uses automatic spreading of opins.
By grouping to output pins in this fashion, if a logic block is completely filled by 6-LUTs,
then the outputs those 6-LUTs take get evenly distributed across all four sides of the CLB instead of clumped on two sides (which is what happens with a more
naive specification).
-->
<direct name="clbouts1" input="fle[3:0].out" output="clb.O"/>
</interconnect>
<!-- Every input pin is driven by 15% of the tracks in a channel, every output pin is driven by 10% of the tracks in a channel -->
<!-- Place this general purpose logic block in any unspecified column -->
</pb_type>
<!-- Define general purpose logic block (CLB) ends -->
</complexblocklist>
</architecture>