OpenFPGA/vpr7_x2p/libarchfpga/arch/sample_arch.xml

816 lines
38 KiB
XML

<!--
Architecture based off Stratix IV
Use closest ifar architecture: K06 N10 45nm fc 0.15 area-delay optimized, scale to 40 nm using linear scaling
n10k06l04.fc15.area1delay1.cmos45nm.bptm.cmos45nm.xml
- because documentation sparser for soft logic (delays not in QUIP), harder to track down, not worth our time considering the level of accuracy is approximate
- delays multiplied by 40/45 to normalize for process difference between stratix 4 and 45 nm technology (called full scaling)
Use delay numbers off Altera device handbook:
http://www.altera.com/literature/hb/stratix-iv/stx4_5v1.pdf
http://www.altera.com/literature/hb/stratix-iv/stx4_siv51004.pdf
http://www.altera.com/literature/hb/stratix-iv/stx4_siv51003.pdf
multipliers at 600 MHz, no detail on 9x9 vs 36x36
- datasheets unclear
- claims 4 18x18 independant multipliers, following test indicates that this is not the case:
created 4 18x18 mulitpliers, logiclocked them to a single DSP block, compile
result - 2 18x18 multipliers got packed together, the other 2 got ejected out of the logiclock region without error
conclusion - just take the 600 MHz as is, and Quartus II logiclock hasn't fixed the bug that I've seen it do to registers when I worked at Altera (ie. eject without warning)
NOTE: Area numbers for hard blocks unknown!
-->
<architecture>
<!-- ODIN II specific config -->
<models>
<model name="multiply">
<input_ports>
<port name="a"/>
<port name="b"/>
</input_ports>
<output_ports>
<port name="out"/>
</output_ports>
</model>
<model name="single_port_ram">
<input_ports>
<port name="we"/> <!-- control -->
<port name="addr"/> <!-- address lines -->
<port name="data"/> <!-- data lines can be broken down into smaller bit widths minimum size 1 -->
<port name="clk" is_clock="1"/> <!-- memories are often clocked -->
</input_ports>
<output_ports>
<port name="out"/> <!-- output can be broken down into smaller bit widths minimum size 1 -->
</output_ports>
</model>
<model name="dual_port_ram">
<input_ports>
<port name="we1"/> <!-- write enable -->
<port name="we2"/> <!-- write enable -->
<port name="addr1"/> <!-- address lines -->
<port name="addr2"/> <!-- address lines -->
<port name="data1"/> <!-- data lines can be broken down into smaller bit widths minimum size 1 -->
<port name="data2"/> <!-- data lines can be broken down into smaller bit widths minimum size 1 -->
<port name="clk" is_clock="1"/> <!-- memories are often clocked -->
</input_ports>
<output_ports>
<port name="out1"/> <!-- output can be broken down into smaller bit widths minimum size 1 -->
<port name="out2"/> <!-- output can be broken down into smaller bit widths minimum size 1 -->
</output_ports>
</model>
<!-- fake carry-chain example -->
<model name="alm">
<input_ports>
<port name="in"/>
<port name="cin"/>
</input_ports>
<output_ports>
<port name="out"/>
<port name="cout"/>
</output_ports>
</model>
<model name="adder">
<input_ports>
<port name="a"/>
<port name="b"/>
<port name="cin"/>
</input_ports>
<output_ports>
<port name="cout"/>
<port name="sumout"/>
</output_ports>
</model>
<!--
<model name="sub">
<input_ports>
<port name="a"/>
<port name="b"/>
<port name="cin"/>
</input_ports>
<output_ports>
<port name="cout"/>
<port name="sumout"/>
</output_ports>
</model>
-->
</models>
<!-- ODIN II specific config ends -->
<!-- Physical descriptions begin (area optimized for N8-K6-L4 -->
<layout auto="1.0"/>
<device>
<sizing R_minW_nmos="6065.520020" R_minW_pmos="18138.500000" ipin_mux_trans_size="1.222260"/>
<timing C_ipin_cblock="0.000000e+00" T_ipin_cblock="7.247000e-11"/>
<area grid_logic_tile_area="14813.392"/>
<chan_width_distr>
<io width="1.000000"/>
<x distr="uniform" peak="1.000000"/>
<y distr="uniform" peak="1.000000"/>
</chan_width_distr>
<switch_block type="wilton" fs="3"/>
</device>
<switchlist>
<switch type="mux" name="0" R="0.000000" Cin="0.000000e+00" Cout="0.000000e+00" Tdel="6.837e-11" mux_trans_size="2.630740" buf_size="27.645901"/>
</switchlist>
<segmentlist>
<segment freq="1.000000" length="4" type="unidir" Rmetal="0.000000" Cmetal="0.000000e+00">
<mux name="0"/>
<sb type="pattern">1 1 1 1 1</sb>
<cb type="pattern">1 1 1 1</cb>
</segment>
</segmentlist>
<complexblocklist>
<!-- 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 -->
<pb_type name="io" capacity="8">
<input name="outpad" num_pins="1"/>
<output name="inpad" num_pins="1"/>
<clock name="clock" num_pins="1"/>
<!-- IOs can operate as either inputs or outputs -->
<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>
<fc default_in_type="frac" default_in_val="0.15" default_out_type="frac" default_out_val="0.125"/>
<!-- 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
-->
<pinlocations pattern="custom">
<loc side="left">io.outpad io.inpad io.clock</loc>
<loc side="top">io.outpad io.inpad io.clock</loc>
<loc side="right">io.outpad io.inpad io.clock</loc>
<loc side="bottom">io.outpad io.inpad io.clock</loc>
</pinlocations>
<gridlocations>
<loc type="perimeter" priority="10"/>
</gridlocations>
</pb_type>
<pb_type name="clb">
<input name="I" num_pins="33" equivalent="true"/>
<output name="O" num_pins="10" equivalent="false"/>
<clock name="clk" num_pins="1"/>
<!-- Describe basic logic element, with ifar delay numbers -->
<pb_type name="ble" num_pb="10">
<input name="in" num_pins="6"/>
<output name="out" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<pb_type name="soft_logic" num_pb="1">
<input name="in" num_pins="6"/>
<output name="out" num_pins="1"/>
<mode name="n1_lut6">
<pb_type name="lut6" blif_model=".names" num_pb="1" class="lut">
<input name="in" num_pins="6" 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="lut6.in" out_port="lut6.out">
2.690e-10
2.690e-10
2.690e-10
2.690e-10
2.690e-10
2.690e-10
</delay_matrix>
</pb_type>
<interconnect>
<direct name="direct1" input="soft_logic.in[5:0]" output="lut6[0:0].in[5:0]"/>
<direct name="direct2" input="lut6[0:0].out" output="soft_logic.out[0:0]">
<!-- CAD related parameters -->
<!-- Advanced "power-user" options: Describe connections that belong to forced pack blocks to give hints to the packer on what blocks to keep together
Assumes pattern nets must be single-fanout
-->
<pack_pattern name="ble" in_port="lut6[0:0].out" out_port="soft_logic.out[0:0]"/>
<!-- CAD related parameters -->
</direct>
</interconnect>
</mode>
</pb_type>
<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="2.448e-10" port="ff.D" clock="clk"/>
<T_clock_to_Q max="7.732e-11" port="ff.Q" clock="clk"/>
</pb_type>
<interconnect>
<!-- Two ff, make ff available to only corresponding luts -->
<direct name="direct1" input="ble.in" output="soft_logic.in"/>
<direct name="direct2" input="soft_logic.out" output="ff.D">
<pack_pattern name="ble" in_port="soft_logic.out" out_port="ff.D"/>
</direct>
<direct name="direct4" input="ble.clk" output="ff.clk"/>
<mux name="mux1" input="ff.Q soft_logic.out" output="ble.out"/>
</interconnect>
</pb_type>
<interconnect>
<complete name="crossbar" input="clb.I ble[9:0].out" output="ble[9:0].in">
<delay_constant max="8.044000e-11" in_port="clb.I" out_port="ble[9:0].in" />
<delay_constant max="7.354000e-11" in_port="ble[9:0].out" out_port="ble[9:0].in" />
</complete>
<complete name="clks" input="clb.clk" output="ble[9:0].clk">
</complete>
<direct name="clbouts" input="ble[9:0].out" output="clb.O">
</direct>
</interconnect>
<fc default_in_type="frac" default_in_val="0.15" default_out_type="frac" default_out_val="0.125"/>
<pinlocations pattern="spread"/>
<gridlocations>
<loc type="fill" priority="1"/>
</gridlocations>
</pb_type>
<!-- This is the 36*36 uniform mult -->
<pb_type name="mult_36" height="4">
<input name="a" num_pins="36"/>
<input name="b" num_pins="36"/>
<output name="out" num_pins="72"/>
<mode name="two_divisible_mult_18x18">
<pb_type name="divisible_mult_18x18" num_pb="2">
<input name="a" num_pins="18"/>
<input name="b" num_pins="18"/>
<output name="out" num_pins="36"/>
<mode name="two_mult_9x9">
<pb_type name="mult_9x9_slice" num_pb="2">
<input name="A_cfg" num_pins="9"/>
<input name="B_cfg" num_pins="9"/>
<output name="OUT_cfg" num_pins="18"/>
<pb_type name="mult_9x9" blif_model=".subckt multiply" num_pb="1">
<input name="a" num_pins="9"/>
<input name="b" num_pins="9"/>
<output name="out" num_pins="18"/>
<delay_constant max="1.667e-9" in_port="mult_9x9.a" out_port="mult_9x9.out"/>
<delay_constant max="1.667e-9" in_port="mult_9x9.b" out_port="mult_9x9.out"/>
</pb_type>
<interconnect>
<direct name="a2a" input="mult_9x9_slice.A_cfg" output="mult_9x9.a">
</direct>
<direct name="b2b" input="mult_9x9_slice.B_cfg" output="mult_9x9.b">
</direct>
<direct name="out2out" input="mult_9x9.out" output="mult_9x9_slice.OUT_cfg">
</direct>
</interconnect>
</pb_type>
<interconnect>
<direct name="a2a" input="divisible_mult_18x18.a" output="mult_9x9_slice[1:0].A_cfg">
</direct>
<direct name="b2b" input="divisible_mult_18x18.b" output="mult_9x9_slice[1:0].B_cfg">
</direct>
<direct name="out2out" input="mult_9x9_slice[1:0].OUT_cfg" output="divisible_mult_18x18.out">
</direct>
</interconnect>
</mode>
<mode name="mult_18x18">
<pb_type name="mult_18x18_slice" num_pb="1">
<input name="A_cfg" num_pins="18"/>
<input name="B_cfg" num_pins="18"/>
<output name="OUT_cfg" num_pins="36"/>
<pb_type name="mult_18x18" blif_model=".subckt multiply" num_pb="1" >
<input name="a" num_pins="18"/>
<input name="b" num_pins="18"/>
<output name="out" num_pins="36"/>
<delay_constant max="1.667e-9" in_port="mult_18x18.a" out_port="mult_18x18.out"/>
<delay_constant max="1.667e-9" in_port="mult_18x18.b" out_port="mult_18x18.out"/>
</pb_type>
<interconnect>
<direct name="a2a" input="mult_18x18_slice.A_cfg" output="mult_18x18.a">
</direct>
<direct name="b2b" input="mult_18x18_slice.B_cfg" output="mult_18x18.b">
</direct>
<direct name="out2out" input="mult_18x18.out" output="mult_18x18_slice.OUT_cfg">
</direct>
</interconnect>
</pb_type>
<interconnect>
<direct name="a2a" input="divisible_mult_18x18.a" output="mult_18x18_slice.A_cfg">
</direct>
<direct name="b2b" input="divisible_mult_18x18.b" output="mult_18x18_slice.B_cfg">
</direct>
<direct name="out2out" input="mult_18x18_slice.OUT_cfg" output="divisible_mult_18x18.out">
</direct>
</interconnect>
</mode>
</pb_type>
<interconnect>
<direct name="a2a" input="mult_36.a" output="divisible_mult_18x18[1:0].a">
</direct>
<direct name="b2b" input="mult_36.b" output="divisible_mult_18x18[1:0].b">
</direct>
<direct name="out2out" input="divisible_mult_18x18[1:0].out" output="mult_36.out">
</direct>
</interconnect>
</mode>
<mode name="mult_36x36">
<pb_type name="mult_36x36_slice" num_pb="1">
<input name="A_cfg" num_pins="36"/>
<input name="B_cfg" num_pins="36"/>
<output name="OUT_cfg" num_pins="72"/>
<pb_type name="mult_36x36" blif_model=".subckt multiply" num_pb="1">
<input name="a" num_pins="36"/>
<input name="b" num_pins="36"/>
<output name="out" num_pins="72"/>
<delay_constant max="1.667e-9" in_port="mult_36x36.a" out_port="mult_36x36.out"/>
<delay_constant max="1.667e-9" in_port="mult_36x36.b" out_port="mult_36x36.out"/>
</pb_type>
<interconnect>
<direct name="a2a" input="mult_36x36_slice.A_cfg" output="mult_36x36.a">
</direct>
<direct name="b2b" input="mult_36x36_slice.B_cfg" output="mult_36x36.b">
</direct>
<direct name="out2out" input="mult_36x36.out" output="mult_36x36_slice.OUT_cfg">
</direct>
</interconnect>
</pb_type>
<interconnect>
<direct name="a2a" input="mult_36.a" output="mult_36x36_slice.A_cfg">
</direct>
<direct name="b2b" input="mult_36.b" output="mult_36x36_slice.B_cfg">
</direct>
<direct name="out2out" input="mult_36x36_slice.OUT_cfg" output="mult_36.out">
</direct>
</interconnect>
</mode>
<fc default_in_type="frac" default_in_val="0.15" default_out_type="frac" default_out_val="0.125"/>
<pinlocations pattern="spread"/>
<gridlocations>
<loc type="col" start="4" repeat="8" priority="2"/>
</gridlocations>
</pb_type>
<!-- Memory based off Stratix IV 144K memory. Setup time set to match flip-flop setup time at 45 nm. Clock to q based off 144K max MHz -->
<pb_type name="memory" height="6">
<input name="addr1" num_pins="17"/>
<input name="addr2" num_pins="17"/>
<input name="data" num_pins="72"/>
<input name="we1" num_pins="1"/>
<input name="we2" num_pins="1"/>
<output name="out" num_pins="72"/>
<clock name="clk" num_pins="1"/>
<mode name="mem_2048x72_sp">
<pb_type name="mem_2048x72_sp" blif_model=".subckt single_port_ram" class="memory" num_pb="1">
<input name="addr" num_pins="11" port_class="address"/>
<input name="data" num_pins="72" port_class="data_in"/>
<input name="we" num_pins="1" port_class="write_en"/>
<output name="out" num_pins="72" port_class="data_out"/>
<clock name="clk" num_pins="1" port_class="clock"/>
<T_setup value="2.448e-10" port="mem_2048x72_sp.addr" clock="clk"/>
<T_setup value="2.448e-10" port="mem_2048x72_sp.data" clock="clk"/>
<T_setup value="2.448e-10" port="mem_2048x72_sp.we" clock="clk"/>
<T_clock_to_Q max="1.852e-9" port="mem_2048x72_sp.out" clock="clk"/>
</pb_type>
<interconnect>
<direct name="address1" input="memory.addr1[10:0]" output="mem_2048x72_sp.addr">
</direct>
<direct name="data1" input="memory.data[71:0]" output="mem_2048x72_sp.data">
</direct>
<direct name="writeen1" input="memory.we1" output="mem_2048x72_sp.we">
</direct>
<direct name="dataout1" input="mem_2048x72_sp.out" output="memory.out[71:0]">
</direct>
<direct name="clk" input="memory.clk" output="mem_2048x72_sp.clk">
</direct>
</interconnect>
</mode>
<mode name="mem_4096x36_dp">
<pb_type name="mem_4096x36_dp" blif_model=".subckt dual_port_ram" class="memory" num_pb="1">
<input name="addr1" num_pins="12" port_class="address1"/>
<input name="addr2" num_pins="12" port_class="address2"/>
<input name="data1" num_pins="36" port_class="data_in1"/>
<input name="data2" num_pins="36" port_class="data_in2"/>
<input name="we1" num_pins="1" port_class="write_en1"/>
<input name="we2" num_pins="1" port_class="write_en2"/>
<output name="out1" num_pins="36" port_class="data_out1"/>
<output name="out2" num_pins="36" port_class="data_out2"/>
<clock name="clk" num_pins="1" port_class="clock"/>
<T_setup value="2.448e-10" port="mem_4096x36_dp.addr1" clock="clk"/>
<T_setup value="2.448e-10" port="mem_4096x36_dp.data1" clock="clk"/>
<T_setup value="2.448e-10" port="mem_4096x36_dp.we1" clock="clk"/>
<T_setup value="2.448e-10" port="mem_4096x36_dp.addr2" clock="clk"/>
<T_setup value="2.448e-10" port="mem_4096x36_dp.data2" clock="clk"/>
<T_setup value="2.448e-10" port="mem_4096x36_dp.we2" clock="clk"/>
<T_clock_to_Q max="1.852e-9" port="mem_4096x36_dp.out1" clock="clk"/>
<T_clock_to_Q max="1.852e-9" port="mem_4096x36_dp.out2" clock="clk"/>
</pb_type>
<interconnect>
<direct name="address1" input="memory.addr1[11:0]" output="mem_4096x36_dp.addr1">
</direct>
<direct name="address2" input="memory.addr2[11:0]" output="mem_4096x36_dp.addr2">
</direct>
<direct name="data1" input="memory.data[35:0]" output="mem_4096x36_dp.data1">
</direct>
<direct name="data2" input="memory.data[71:36]" output="mem_4096x36_dp.data2">
</direct>
<direct name="writeen1" input="memory.we1" output="mem_4096x36_dp.we1">
</direct>
<direct name="writeen2" input="memory.we2" output="mem_4096x36_dp.we2">
</direct>
<direct name="dataout1" input="mem_4096x36_dp.out1" output="memory.out[35:0]">
</direct>
<direct name="dataout2" input="mem_4096x36_dp.out2" output="memory.out[71:36]">
</direct>
<direct name="clk" input="memory.clk" output="mem_4096x36_dp.clk">
</direct>
</interconnect>
</mode>
<mode name="mem_4096x36_sp">
<pb_type name="mem_4096x36_sp" blif_model=".subckt single_port_ram" class="memory" num_pb="1">
<input name="addr" num_pins="12" port_class="address"/>
<input name="data" num_pins="36" port_class="data_in"/>
<input name="we" num_pins="1" port_class="write_en"/>
<output name="out" num_pins="36" port_class="data_out"/>
<clock name="clk" num_pins="1" port_class="clock"/>
<T_setup value="2.448e-10" port="mem_4096x36_sp.addr" clock="clk"/>
<T_setup value="2.448e-10" port="mem_4096x36_sp.data" clock="clk"/>
<T_setup value="2.448e-10" port="mem_4096x36_sp.we" clock="clk"/>
<T_clock_to_Q max="1.852e-9" port="mem_4096x36_sp.out" clock="clk"/>
</pb_type>
<interconnect>
<direct name="address1" input="memory.addr1[11:0]" output="mem_4096x36_sp.addr">
</direct>
<direct name="data1" input="memory.data[35:0]" output="mem_4096x36_sp.data">
</direct>
<direct name="writeen1" input="memory.we1" output="mem_4096x36_sp.we">
</direct>
<direct name="dataout1" input="mem_4096x36_sp.out" output="memory.out[35:0]">
</direct>
<direct name="clk" input="memory.clk" output="mem_4096x36_sp.clk">
</direct>
</interconnect>
</mode>
<mode name="mem_9182x18_dp">
<pb_type name="mem_9182x18_dp" blif_model=".subckt dual_port_ram" class="memory" num_pb="1">
<input name="addr1" num_pins="13" port_class="address1"/>
<input name="addr2" num_pins="13" port_class="address2"/>
<input name="data1" num_pins="18" port_class="data_in1"/>
<input name="data2" num_pins="18" port_class="data_in2"/>
<input name="we1" num_pins="1" port_class="write_en1"/>
<input name="we2" num_pins="1" port_class="write_en2"/>
<output name="out1" num_pins="18" port_class="data_out1"/>
<output name="out2" num_pins="18" port_class="data_out2"/>
<clock name="clk" num_pins="1" port_class="clock"/>
<T_setup value="2.448e-10" port="mem_9182x18_dp.addr1" clock="clk"/>
<T_setup value="2.448e-10" port="mem_9182x18_dp.data1" clock="clk"/>
<T_setup value="2.448e-10" port="mem_9182x18_dp.we1" clock="clk"/>
<T_setup value="2.448e-10" port="mem_9182x18_dp.addr2" clock="clk"/>
<T_setup value="2.448e-10" port="mem_9182x18_dp.data2" clock="clk"/>
<T_setup value="2.448e-10" port="mem_9182x18_dp.we2" clock="clk"/>
<T_clock_to_Q max="1.852e-9" port="mem_9182x18_dp.out1" clock="clk"/>
<T_clock_to_Q max="1.852e-9" port="mem_9182x18_dp.out2" clock="clk"/>
</pb_type>
<interconnect>
<direct name="address1" input="memory.addr1[12:0]" output="mem_9182x18_dp.addr1">
</direct>
<direct name="address2" input="memory.addr2[12:0]" output="mem_9182x18_dp.addr2">
</direct>
<direct name="data1" input="memory.data[17:0]" output="mem_9182x18_dp.data1">
</direct>
<direct name="data2" input="memory.data[35:18]" output="mem_9182x18_dp.data2">
</direct>
<direct name="writeen1" input="memory.we1" output="mem_9182x18_dp.we1">
</direct>
<direct name="writeen2" input="memory.we2" output="mem_9182x18_dp.we2">
</direct>
<direct name="dataout1" input="mem_9182x18_dp.out1" output="memory.out[17:0]">
</direct>
<direct name="dataout2" input="mem_9182x18_dp.out2" output="memory.out[35:18]">
</direct>
<direct name="clk" input="memory.clk" output="mem_9182x18_dp.clk">
</direct>
</interconnect>
</mode>
<mode name="mem_9182x18_sp">
<pb_type name="mem_9182x18_sp" blif_model=".subckt single_port_ram" class="memory" num_pb="1">
<input name="addr" num_pins="13" port_class="address"/>
<input name="data" num_pins="18" port_class="data_in"/>
<input name="we" num_pins="1" port_class="write_en"/>
<output name="out" num_pins="18" port_class="data_out"/>
<clock name="clk" num_pins="1" port_class="clock"/>
<T_setup value="2.448e-10" port="mem_9182x18_sp.addr" clock="clk"/>
<T_setup value="2.448e-10" port="mem_9182x18_sp.data" clock="clk"/>
<T_setup value="2.448e-10" port="mem_9182x18_sp.we" clock="clk"/>
<T_clock_to_Q max="1.852e-9" port="mem_9182x18_sp.out" clock="clk"/>
</pb_type>
<interconnect>
<direct name="address1" input="memory.addr1[12:0]" output="mem_9182x18_sp.addr">
</direct>
<direct name="data1" input="memory.data[17:0]" output="mem_9182x18_sp.data">
</direct>
<direct name="writeen1" input="memory.we1" output="mem_9182x18_sp.we">
</direct>
<direct name="dataout1" input="mem_9182x18_sp.out" output="memory.out[17:0]">
</direct>
<direct name="clk" input="memory.clk" output="mem_9182x18_sp.clk">
</direct>
</interconnect>
</mode>
<mode name="mem_18194x9_dp">
<pb_type name="mem_18194x9_dp" blif_model=".subckt dual_port_ram" class="memory" num_pb="1">
<input name="addr1" num_pins="14" port_class="address1"/>
<input name="addr2" num_pins="14" port_class="address2"/>
<input name="data1" num_pins="9" port_class="data_in1"/>
<input name="data2" num_pins="9" port_class="data_in2"/>
<input name="we1" num_pins="1" port_class="write_en1"/>
<input name="we2" num_pins="1" port_class="write_en2"/>
<output name="out1" num_pins="9" port_class="data_out1"/>
<output name="out2" num_pins="9" port_class="data_out2"/>
<clock name="clk" num_pins="1" port_class="clock"/>
<T_setup value="2.448e-10" port="mem_18194x9_dp.addr1" clock="clk"/>
<T_setup value="2.448e-10" port="mem_18194x9_dp.data1" clock="clk"/>
<T_setup value="2.448e-10" port="mem_18194x9_dp.we1" clock="clk"/>
<T_setup value="2.448e-10" port="mem_18194x9_dp.addr2" clock="clk"/>
<T_setup value="2.448e-10" port="mem_18194x9_dp.data2" clock="clk"/>
<T_setup value="2.448e-10" port="mem_18194x9_dp.we2" clock="clk"/>
<T_clock_to_Q max="1.852e-9" port="mem_18194x9_dp.out1" clock="clk"/>
<T_clock_to_Q max="1.852e-9" port="mem_18194x9_dp.out2" clock="clk"/>
</pb_type>
<interconnect>
<direct name="address1" input="memory.addr1[13:0]" output="mem_18194x9_dp.addr1">
</direct>
<direct name="address2" input="memory.addr2[13:0]" output="mem_18194x9_dp.addr2">
</direct>
<direct name="data1" input="memory.data[8:0]" output="mem_18194x9_dp.data1">
</direct>
<direct name="data2" input="memory.data[17:9]" output="mem_18194x9_dp.data2">
</direct>
<direct name="writeen1" input="memory.we1" output="mem_18194x9_dp.we1">
</direct>
<direct name="writeen2" input="memory.we2" output="mem_18194x9_dp.we2">
</direct>
<direct name="dataout1" input="mem_18194x9_dp.out1" output="memory.out[8:0]">
</direct>
<direct name="dataout2" input="mem_18194x9_dp.out2" output="memory.out[17:9]">
</direct>
<direct name="clk" input="memory.clk" output="mem_18194x9_dp.clk">
</direct>
</interconnect>
</mode>
<mode name="mem_18194x9_sp">
<pb_type name="mem_18194x9_sp" blif_model=".subckt single_port_ram" class="memory" num_pb="1">
<input name="addr" num_pins="14" port_class="address"/>
<input name="data" num_pins="9" port_class="data_in"/>
<input name="we" num_pins="1" port_class="write_en"/>
<output name="out" num_pins="9" port_class="data_out"/>
<clock name="clk" num_pins="1" port_class="clock"/>
<T_setup value="2.448e-10" port="mem_18194x9_sp.addr" clock="clk"/>
<T_setup value="2.448e-10" port="mem_18194x9_sp.data" clock="clk"/>
<T_setup value="2.448e-10" port="mem_18194x9_sp.we" clock="clk"/>
<T_clock_to_Q max="1.852e-9" port="mem_18194x9_sp.out" clock="clk"/>
</pb_type>
<interconnect>
<direct name="address1" input="memory.addr1[13:0]" output="mem_18194x9_sp.addr">
</direct>
<direct name="data1" input="memory.data[8:0]" output="mem_18194x9_sp.data">
</direct>
<direct name="writeen1" input="memory.we1" output="mem_18194x9_sp.we">
</direct>
<direct name="dataout1" input="mem_18194x9_sp.out" output="memory.out[8:0]">
</direct>
<direct name="clk" input="memory.clk" output="mem_18194x9_sp.clk">
</direct>
</interconnect>
</mode>
<fc default_in_type="frac" default_in_val="0.15" default_out_type="frac" default_out_val="0.125"/>
<pinlocations pattern="spread"/>
<gridlocations>
<loc type="col" start="2" repeat="8" priority="2"/>
</gridlocations>
</pb_type>
<!-- fake carry-chain example -->
<pb_type name="carry_chain_example">
<input name="I" num_pins="15" equivalent="true"/>
<input name="cin" num_pins="1"/>
<output name="O" num_pins="4" equivalent="false"/>
<output name="cout" num_pins="1" equivalent="false"/>
<clock name="clk" num_pins="1"/>
<!-- Describe basic logic element, with ifar delay numbers -->
<pb_type name="ble" num_pb="4">
<input name="in" num_pins="6"/>
<input name="cin" num_pins="1"/>
<output name="out" num_pins="1"/>
<output name="cout" num_pins="1"/>
<clock name="clk" num_pins="1"/>
<pb_type name="alm" blif_model=".subckt alm" num_pb="1">
<input name="in" num_pins="6"/>
<input name="cin" num_pins="1" chain="carry_chain_alm"/>
<output name="out" num_pins="1"/>
<output name="cout" num_pins="1" chain="carry_chain_alm"/>
<!-- LUT timing using delay matrix -->
<delay_matrix type="max" in_port="alm.in" out_port="alm.out">
2.690e-10
2.690e-10
2.690e-10
2.690e-10
2.690e-10
2.690e-10
</delay_matrix>
<!-- LUT timing using delay matrix -->
<delay_matrix type="max" in_port="alm.cin" out_port="alm.out">
2.690e-10
</delay_matrix>
<!-- LUT timing using delay matrix -->
<delay_matrix type="max" in_port="alm.cin" out_port="alm.cout">
1.690e-10
</delay_matrix>
</pb_type>
<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="2.448e-10" port="ff.D" clock="clk"/>
<T_clock_to_Q max="7.732e-11" port="ff.Q" clock="clk"/>
</pb_type>
<interconnect>
<!-- Two ff, make ff available to only corresponding luts -->
<complete name="complete1" input="ble.in" output="alm.in ff.D"/>
<direct name="direct4" input="ble.clk" output="ff.clk"/>
<direct name="direct5" input="ble.cin" output="alm.cin"/>
<direct name="direct6" input="alm.cout" output="ble.cout"/>
<mux name="mux1" input="ff.Q alm.out" output="ble.out"/>
</interconnect>
</pb_type>
<interconnect>
<complete name="crossbar" input="carry_chain_example.I ble[3:0].out" output="ble[3:0].in">
<delay_constant max="8.044000e-11" in_port="carry_chain_example.I" out_port="ble[3:0].in" />
<delay_constant max="7.354000e-11" in_port="ble[3:0].out" out_port="ble[3:0].in" />
</complete>
<complete name="clks" input="carry_chain_example.clk" output="ble[3:0].clk">
</complete>
<direct name="clbouts" input="ble[3:0].out" output="carry_chain_example.O">
</direct>
<direct name="carry1" input="ble[0:0].cout" output="ble[1:1].cin"/>
<direct name="carry2" input="ble[1:1].cout" output="ble[2:2].cin"/>
<direct name="carry3" input="ble[2:2].cout" output="ble[3:3].cin"/>
<direct name="carry4" input="ble[3:3].cout" output="carry_chain_example.cout"/>
</interconnect>
<fc default_in_type="frac" default_in_val="0.15" default_out_type="frac" default_out_val="0.125"/>
<pinlocations pattern="spread"/>
<gridlocations>
<loc type="col" start="7" repeat="50" priority="7"/>
</gridlocations>
</pb_type>
<!-- This is a basic ripple-carry adder primitive
We will take care of the carry chain for it later, for now, get something that goes through the flow so that Odin II can be tested
-->
<pb_type name="adder" height="1">
<input name="a" num_pins="4"/>
<input name="b" num_pins="4"/>
<input name="cin" num_pins="1"/>
<output name="cout" num_pins="1"/>
<output name="sumout" num_pins="4"/>
<mode name="sample_adder">
<pb_type name="sample_adder" blif_model=".subckt adder" num_pb="1">
<input name="a" num_pins="4"/>
<input name="b" num_pins="4"/>
<input name="cin" num_pins="1"/>
<output name="cout" num_pins="1"/>
<output name="sumout" num_pins="4"/>
<delay_constant max="1.667e-9" in_port="sample_adder.a" out_port="sample_adder.cout"/>
<delay_constant max="1.667e-9" in_port="sample_adder.b" out_port="sample_adder.cout"/>
<delay_constant max="1.667e-9" in_port="sample_adder.cin" out_port="sample_adder.cout"/>
<delay_constant max="1.667e-9" in_port="sample_adder.a" out_port="sample_adder.sumout"/>
<delay_constant max="1.667e-9" in_port="sample_adder.b" out_port="sample_adder.sumout"/>
<delay_constant max="1.667e-9" in_port="sample_adder.cin" out_port="sample_adder.sumout"/>
</pb_type>
<interconnect>
<direct name="a2a" input="adder.a" output="sample_adder.a">
</direct>
<direct name="b2b" input="adder.b" output="sample_adder.b">
</direct>
<direct name="c2c" input="adder.cin" output="sample_adder.cin">
</direct>
<direct name="cout" input="sample_adder.cout" output="adder.cout">
</direct>
<direct name="sumout" input="sample_adder.sumout" output="adder.sumout">
</direct>
</interconnect>
</mode>
<fc default_in_type="frac" default_in_val="0.15" default_out_type="frac" default_out_val="0.125"/>
<pinlocations pattern="spread"/>
<gridlocations>
<loc type="col" start="2" repeat="13" priority="10"/>
</gridlocations>
</pb_type>
<!--
<pb_type name="sub" height="1">
<input name="a" num_pins="4"/>
<input name="b" num_pins="4"/>
<input name="cin" num_pins="1"/>
<output name="cout" num_pins="1"/>
<output name="sumout" num_pins="4"/>
<mode name="sample_sub">
<pb_type name="sample_sub" blif_model=".subckt sub" num_pb="1">
<input name="a" num_pins="4"/>
<input name="b" num_pins="4"/>
<input name="cin" num_pins="1"/>
<output name="cout" num_pins="1"/>
<output name="sumout" num_pins="4"/>
<delay_constant max="1.667e-9" in_port="sample_sub.a" out_port="sample_sub.cout"/>
<delay_constant max="1.667e-9" in_port="sample_sub.b" out_port="sample_sub.cout"/>
<delay_constant max="1.667e-9" in_port="sample_sub.cin" out_port="sample_sub.cout"/>
<delay_constant max="1.667e-9" in_port="sample_sub.a" out_port="sample_sub.sumout"/>
<delay_constant max="1.667e-9" in_port="sample_sub.b" out_port="sample_sub.sumout"/>
<delay_constant max="1.667e-9" in_port="sample_sub.cin" out_port="sample_sub.sumout"/>
</pb_type>
<interconnect>
<direct name="a2a" input="sub.a" output="sample_sub.a">
</direct>
<direct name="b2b" input="sub.b" output="sample_sub.b">
</direct>
<direct name="c2c" input="sub.cin" output="sample_sub.cin">
</direct>
<direct name="cout" input="sample_sub.cout" output="sub.cout">
</direct>
<direct name="sumout" input="sample_sub.sumout" output="sub.sumout">
</direct>
</interconnect>
</mode>
<fc default_in_type="frac" default_in_val="0.15" default_out_type="frac" default_out_val="0.125"/>
<pinlocations pattern="spread"/>
<gridlocations>
<loc type="col" start="2" repeat="13" priority="10"/>
</gridlocations>
</pb_type>
-->
</complexblocklist>
</architecture>