Updated demo projects
This commit is contained in:
parent
042a9c0c0a
commit
23e8a4f857
|
@ -8,6 +8,8 @@ RUN apt-get install -y nodejs
|
||||||
RUN apt-get install tree
|
RUN apt-get install tree
|
||||||
RUN code-server --install-extension ms-python.python
|
RUN code-server --install-extension ms-python.python
|
||||||
RUN code-server --install-extension mechatroner.rainbow-csv
|
RUN code-server --install-extension mechatroner.rainbow-csv
|
||||||
|
RUN code-server --install-extension wavetrace.wavetrace
|
||||||
|
RUN code-server --install-extension dotjoshjohnson.xml
|
||||||
|
|
||||||
RUN usermod -u 2000 openfpga_user
|
RUN usermod -u 2000 openfpga_user
|
||||||
RUN groupmod -g 2000 openfpga_user
|
RUN groupmod -g 2000 openfpga_user
|
||||||
|
|
|
@ -1,287 +1,191 @@
|
||||||
<?xml version="1.0" ?><!--
|
<?xml version="1.0" ?>
|
||||||
Architecture with no fracturable LUTs
|
<architecture>
|
||||||
|
<models>
|
||||||
- 40 nm technology
|
<!-- A virtual model for I/O to be used in the physical mode of io block -->
|
||||||
- General purpose logic block:
|
<model name="io">
|
||||||
K = 6, N = 10
|
<input_ports>
|
||||||
- Routing architecture: L = 4, fc_in = 0.15, Fc_out = 0.1
|
<port name="outpad"/>
|
||||||
|
</input_ports>
|
||||||
Details on Modelling:
|
<output_ports>
|
||||||
|
<port name="inpad"/>
|
||||||
Based on flagship k6_frac_N10_mem32K_40nm.xml architecture. This architecture has no fracturable LUTs nor any heterogeneous blocks.
|
</output_ports>
|
||||||
|
</model>
|
||||||
|
</models>
|
||||||
Authors: Jason Luu, Jeff Goeders, Vaughn Betz
|
<tiles>
|
||||||
--><architecture>
|
<tile name="io" area="0">
|
||||||
<models>
|
<sub_tile name="io" capacity="8">
|
||||||
<!-- A virtual model for I/O to be used in the physical mode of io block -->
|
<equivalent_sites>
|
||||||
<model name="io">
|
<site pb_type="io"/>
|
||||||
<input_ports>
|
</equivalent_sites>
|
||||||
<port name="outpad"/>
|
<input name="outpad" num_pins="1"/>
|
||||||
</input_ports>
|
<output name="inpad" num_pins="1"/>
|
||||||
<output_ports>
|
<fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10"/>
|
||||||
<port name="inpad"/>
|
<pinlocations pattern="custom">
|
||||||
</output_ports>
|
<loc side="left">io.outpad io.inpad</loc>
|
||||||
</model>
|
<loc side="top">io.outpad io.inpad</loc>
|
||||||
</models>
|
<loc side="right">io.outpad io.inpad</loc>
|
||||||
<tiles>
|
<loc side="bottom">io.outpad io.inpad</loc>
|
||||||
<tile name="io" area="0"> <sub_tile name="io" capacity="8">
|
</pinlocations>
|
||||||
<equivalent_sites>
|
</sub_tile>
|
||||||
<site pb_type="io"/>
|
</tile>
|
||||||
</equivalent_sites>
|
<tile name="clb" area="53894">
|
||||||
<input name="outpad" num_pins="1"/>
|
<sub_tile name="clb">
|
||||||
<output name="inpad" num_pins="1"/>
|
<equivalent_sites>
|
||||||
<fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10"/>
|
<site pb_type="clb"/>
|
||||||
<pinlocations pattern="custom">
|
</equivalent_sites>
|
||||||
<loc side="left">io.outpad io.inpad</loc>
|
<input name="I" num_pins="40" equivalent="full"/>
|
||||||
<loc side="top">io.outpad io.inpad</loc>
|
<output name="O" num_pins="10" equivalent="none"/>
|
||||||
<loc side="right">io.outpad io.inpad</loc>
|
<clock name="clk" num_pins="1"/>
|
||||||
<loc side="bottom">io.outpad io.inpad</loc>
|
<fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10"/>
|
||||||
</pinlocations>
|
<pinlocations pattern="spread"/>
|
||||||
</sub_tile> </tile>
|
</sub_tile>
|
||||||
<tile name="clb" area="53894"> <sub_tile name="clb">
|
</tile>
|
||||||
<equivalent_sites>
|
</tiles>
|
||||||
<site pb_type="clb"/>
|
<!-- ODIN II specific config ends -->
|
||||||
</equivalent_sites>
|
<!-- Physical descriptions begin -->
|
||||||
<input name="I" num_pins="40" equivalent="full"/>
|
<layout tileable="true">
|
||||||
<output name="O" num_pins="10" equivalent="none"/>
|
<auto_layout aspect_ratio="1.0">
|
||||||
<clock name="clk" num_pins="1"/>
|
<!--Perimeter of 'io' blocks with 'EMPTY' blocks at corners-->
|
||||||
<fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10"/>
|
<perimeter type="io" priority="100"/>
|
||||||
<pinlocations pattern="spread"/>
|
<corners type="EMPTY" priority="101"/>
|
||||||
</sub_tile> </tile>
|
<!--Fill with 'clb'-->
|
||||||
</tiles>
|
<fill type="clb" priority="10"/>
|
||||||
<!-- ODIN II specific config ends -->
|
</auto_layout>
|
||||||
<!-- Physical descriptions begin -->
|
</layout>
|
||||||
<layout tileable="true">
|
<device>
|
||||||
<auto_layout aspect_ratio="1.0">
|
<sizing R_minW_nmos="8926" R_minW_pmos="16067"/>
|
||||||
<!--Perimeter of 'io' blocks with 'EMPTY' blocks at corners-->
|
<area grid_logic_tile_area="0"/>
|
||||||
<perimeter type="io" priority="100"/>
|
<chan_width_distr>
|
||||||
<corners type="EMPTY" priority="101"/>
|
<x distr="uniform" peak="1.000000"/>
|
||||||
<!--Fill with 'clb'-->
|
<y distr="uniform" peak="1.000000"/>
|
||||||
<fill type="clb" priority="10"/>
|
</chan_width_distr>
|
||||||
</auto_layout>
|
<switch_block type="wilton" fs="3"/>
|
||||||
</layout>
|
<connection_block input_switch_name="ipin_cblock"/>
|
||||||
<device>
|
</device>
|
||||||
<!-- VB & JL: Using Ian Kuon's transistor sizing and drive strength data for routing, at 40 nm. Ian used BPTM
|
<switchlist>
|
||||||
models. We are modifying the delay values however, to include metal C and R, which allows more architecture
|
<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"/>
|
||||||
experimentation. We are also modifying the relative resistance of PMOS to be 1.8x that of NMOS
|
<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"/>
|
||||||
(vs. Ian's 3x) as 1.8x lines up with Jeff G's data from a 45 nm process (and is more typical of
|
</switchlist>
|
||||||
45 nm in general). I'm upping the Rmin_nmos from Ian's just over 6k to nearly 9k, and dropping
|
<segmentlist>
|
||||||
RminW_pmos from 18k to 16k to hit this 1.8x ratio, while keeping the delays of buffers approximately
|
<segment name="L4" freq="1.000000" length="4" type="unidir" Rmetal="101" Cmetal="22.5e-15">
|
||||||
lined up with Stratix IV.
|
<mux name="0"/>
|
||||||
We are using Jeff G.'s capacitance data for 45 nm (in tech/ptm_45nm).
|
<sb type="pattern">1 1 1 1 1</sb>
|
||||||
Jeff's tables list C in for transistors with widths in multiples of the minimum feature size (45 nm).
|
<cb type="pattern">1 1 1 1</cb>
|
||||||
The minimum contactable transistor is 2.5 * 45 nm, so I need to multiply drive strength sizes in this file
|
</segment>
|
||||||
by 2.5x when looking up in Jeff's tables.
|
</segmentlist>
|
||||||
The delay values are lined up with Stratix IV, which has an architecture similar to this
|
<complexblocklist>
|
||||||
proposed FPGA, and which is also 40 nm
|
<pb_type name="io">
|
||||||
C_ipin_cblock: input capacitance of a track buffer, which VPR assumes is a single-stage
|
<input name="outpad" num_pins="1"/>
|
||||||
4x minimum drive strength buffer. -->
|
<output name="inpad" num_pins="1"/>
|
||||||
<sizing R_minW_nmos="8926" R_minW_pmos="16067"/>
|
<mode name="physical" disable_packing="true">
|
||||||
<!-- The grid_logic_tile_area below will be used for all blocks that do not explicitly set their own (non-routing)
|
<pb_type name="iopad" blif_model=".subckt io" num_pb="1">
|
||||||
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"/>
|
<input name="outpad" num_pins="1"/>
|
||||||
<output name="inpad" num_pins="1"/>
|
<output name="inpad" num_pins="1"/>
|
||||||
<!-- A mode denotes the physical implementation of an I/O
|
</pb_type>
|
||||||
This mode will be not packable but is mainly used for fabric verilog generation
|
<interconnect>
|
||||||
-->
|
<direct name="outpad" input="io.outpad" output="iopad.outpad">
|
||||||
<mode name="physical" disable_packing="true">
|
<delay_constant max="1.394e-11" in_port="io.outpad" out_port="iopad.outpad"/>
|
||||||
<pb_type name="iopad" blif_model=".subckt io" num_pb="1">
|
</direct>
|
||||||
<input name="outpad" num_pins="1"/>
|
<direct name="inpad" input="iopad.inpad" output="io.inpad">
|
||||||
<output name="inpad" num_pins="1"/>
|
<delay_constant max="4.243e-11" in_port="iopad.inpad" out_port="io.inpad"/>
|
||||||
</pb_type>
|
</direct>
|
||||||
<interconnect>
|
</interconnect>
|
||||||
<direct name="outpad" input="io.outpad" output="iopad.outpad">
|
</mode>
|
||||||
<delay_constant max="1.394e-11" in_port="io.outpad" out_port="iopad.outpad"/>
|
<mode name="inpad">
|
||||||
</direct>
|
<pb_type name="inpad" blif_model=".input" num_pb="1">
|
||||||
<direct name="inpad" input="iopad.inpad" output="io.inpad">
|
<output name="inpad" num_pins="1"/>
|
||||||
<delay_constant max="4.243e-11" in_port="iopad.inpad" out_port="io.inpad"/>
|
</pb_type>
|
||||||
</direct>
|
<interconnect>
|
||||||
</interconnect>
|
<direct name="inpad" input="inpad.inpad" output="io.inpad">
|
||||||
</mode>
|
<delay_constant max="4.243e-11" in_port="inpad.inpad" out_port="io.inpad"/>
|
||||||
<!-- IOs can operate as either inputs or outputs.
|
</direct>
|
||||||
Delays below come from Ian Kuon. They are small, so they should be interpreted as
|
</interconnect>
|
||||||
the delays to and from registers in the I/O (and generally I/Os are registered
|
</mode>
|
||||||
today and that is when you timing analyze them.
|
<mode name="outpad">
|
||||||
-->
|
<pb_type name="outpad" blif_model=".output" num_pb="1">
|
||||||
<mode name="inpad">
|
<input name="outpad" num_pins="1"/>
|
||||||
<pb_type name="inpad" blif_model=".input" num_pb="1">
|
</pb_type>
|
||||||
<output name="inpad" num_pins="1"/>
|
<interconnect>
|
||||||
</pb_type>
|
<direct name="outpad" input="io.outpad" output="outpad.outpad">
|
||||||
<interconnect>
|
<delay_constant max="1.394e-11" in_port="io.outpad" out_port="outpad.outpad"/>
|
||||||
<direct name="inpad" input="inpad.inpad" output="io.inpad">
|
</direct>
|
||||||
<delay_constant max="4.243e-11" in_port="inpad.inpad" out_port="io.inpad"/>
|
</interconnect>
|
||||||
</direct>
|
</mode>
|
||||||
</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 -->
|
||||||
</mode>
|
<!-- IOs go on the periphery of the FPGA, for consistency,
|
||||||
<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.
|
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
|
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 -->
|
<!-- Place I/Os on the sides of the FPGA -->
|
||||||
<power method="ignore"/>
|
<power method="ignore"/>
|
||||||
</pb_type>
|
</pb_type>
|
||||||
<!-- Define I/O pads ends -->
|
<pb_type name="clb">
|
||||||
<!-- Define general purpose logic block (CLB) begin -->
|
<input name="I" num_pins="40" equivalent="full"/>
|
||||||
<!--- Area calculation: Total Stratix IV tile area is about 8100 um^2, and a minimum width transistor
|
<output name="O" num_pins="10" equivalent="none"/>
|
||||||
area is 60 L^2 yields a tile area of 84375 MWTAs.
|
<clock name="clk" num_pins="1"/>
|
||||||
Routing at W=300 is 30481 MWTAs, leaving us with a total of 53000 MWTAs for logic block area
|
<pb_type name="fle" num_pb="10">
|
||||||
This means that only 37% of our area is in the general routing, and 63% is inside the logic
|
<input name="in" num_pins="6"/>
|
||||||
block. Note that the crossbar / local interconnect is considered part of the logic block
|
<output name="out" num_pins="1"/>
|
||||||
area in this analysis. That is a lower proportion of of routing area than most academics
|
<clock name="clk" num_pins="1"/>
|
||||||
assume, but note that the total routing area really includes the crossbar, which would push
|
<!-- 6-LUT mode definition begin -->
|
||||||
routing area up significantly, we estimate into the ~70% range.
|
<mode name="n1_lut6">
|
||||||
-->
|
<!-- Define 6-LUT mode -->
|
||||||
<pb_type name="clb">
|
<pb_type name="ble6" num_pb="1">
|
||||||
<input name="I" num_pins="40" equivalent="full"/>
|
<input name="in" num_pins="6"/>
|
||||||
<output name="O" num_pins="10" equivalent="none"/>
|
<output name="out" num_pins="1"/>
|
||||||
<clock name="clk" num_pins="1"/>
|
<clock name="clk" num_pins="1"/>
|
||||||
<!-- Describe basic logic element.
|
<!-- Define LUT -->
|
||||||
Each basic logic element has a 6-LUT that can be optionally registered
|
<pb_type name="lut6" blif_model=".names" num_pb="1" class="lut">
|
||||||
-->
|
<input name="in" num_pins="6" port_class="lut_in"/>
|
||||||
<pb_type name="fle" num_pb="10">
|
<output name="out" num_pins="1" port_class="lut_out"/>
|
||||||
<input name="in" num_pins="6"/>
|
<delay_matrix type="max" in_port="lut6.in" out_port="lut6.out">
|
||||||
<output name="out" num_pins="1"/>
|
261e-12
|
||||||
<clock name="clk" num_pins="1"/>
|
261e-12
|
||||||
<!-- 6-LUT mode definition begin -->
|
261e-12
|
||||||
<mode name="n1_lut6">
|
261e-12
|
||||||
<!-- Define 6-LUT mode -->
|
261e-12
|
||||||
<pb_type name="ble6" num_pb="1">
|
261e-12
|
||||||
<input name="in" num_pins="6"/>
|
</delay_matrix>
|
||||||
<output name="out" num_pins="1"/>
|
</pb_type>
|
||||||
<clock name="clk" num_pins="1"/>
|
<!-- Define flip-flop -->
|
||||||
<!-- Define LUT -->
|
<pb_type name="ff" blif_model=".latch" num_pb="1" class="flipflop">
|
||||||
<pb_type name="lut6" blif_model=".names" num_pb="1" class="lut">
|
<input name="D" num_pins="1" port_class="D"/>
|
||||||
<input name="in" num_pins="6" port_class="lut_in"/>
|
<output name="Q" num_pins="1" port_class="Q"/>
|
||||||
<output name="out" num_pins="1" port_class="lut_out"/>
|
<clock name="clk" num_pins="1" port_class="clock"/>
|
||||||
<!-- LUT timing using delay matrix -->
|
<T_setup value="66e-12" port="ff.D" clock="clk"/>
|
||||||
<!-- These are the physical delay inputs on a Stratix IV LUT but because VPR cannot do LUT rebalancing,
|
<T_clock_to_Q max="124e-12" port="ff.Q" clock="clk"/>
|
||||||
we instead take the average of these numbers to get more stable results
|
</pb_type>
|
||||||
82e-12
|
<interconnect>
|
||||||
173e-12
|
<direct name="direct1" input="ble6.in" output="lut6[0:0].in"/>
|
||||||
261e-12
|
<direct name="direct2" input="lut6.out" output="ff.D">
|
||||||
263e-12
|
<!-- Advanced user option that tells CAD tool to find LUT+FF pairs in netlist -->
|
||||||
398e-12
|
<pack_pattern name="ble6" in_port="lut6.out" out_port="ff.D"/>
|
||||||
397e-12
|
</direct>
|
||||||
-->
|
<direct name="direct3" input="ble6.clk" output="ff.clk"/>
|
||||||
<delay_matrix type="max" in_port="lut6.in" out_port="lut6.out">
|
<mux name="mux1" input="ff.Q lut6.out" output="ble6.out">
|
||||||
261e-12
|
<!-- LUT to output is faster than FF to output on a Stratix IV -->
|
||||||
261e-12
|
<delay_constant max="25e-12" in_port="lut6.out" out_port="ble6.out"/>
|
||||||
261e-12
|
<delay_constant max="45e-12" in_port="ff.Q" out_port="ble6.out"/>
|
||||||
261e-12
|
</mux>
|
||||||
261e-12
|
</interconnect>
|
||||||
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="ble6.in" output="lut6[0:0].in"/>
|
|
||||||
<direct name="direct2" input="lut6.out" output="ff.D">
|
|
||||||
<!-- Advanced user option that tells CAD tool to find LUT+FF pairs in netlist -->
|
|
||||||
<pack_pattern name="ble6" in_port="lut6.out" out_port="ff.D"/>
|
|
||||||
</direct>
|
|
||||||
<direct name="direct3" input="ble6.clk" output="ff.clk"/>
|
|
||||||
<mux name="mux1" input="ff.Q lut6.out" output="ble6.out">
|
|
||||||
<!-- LUT to output is faster than FF to output on a Stratix IV -->
|
|
||||||
<delay_constant max="25e-12" in_port="lut6.out" out_port="ble6.out"/>
|
|
||||||
<delay_constant max="45e-12" in_port="ff.Q" out_port="ble6.out"/>
|
|
||||||
</mux>
|
|
||||||
</interconnect>
|
|
||||||
</pb_type>
|
|
||||||
<interconnect>
|
|
||||||
<direct name="direct1" input="fle.in" output="ble6.in"/>
|
|
||||||
<direct name="direct2" input="ble6.out" output="fle.out[0:0]"/>
|
|
||||||
<direct name="direct3" input="fle.clk" output="ble6.clk"/>
|
|
||||||
</interconnect>
|
|
||||||
</mode>
|
|
||||||
<!-- 6-LUT mode definition end -->
|
|
||||||
</pb_type>
|
</pb_type>
|
||||||
<interconnect>
|
<interconnect>
|
||||||
<!-- We use a full crossbar to get logical equivalence at inputs of CLB
|
<direct name="direct1" input="fle.in" output="ble6.in"/>
|
||||||
The delays below come from Stratix IV. the delay through a connection block
|
<direct name="direct2" input="ble6.out" output="fle.out[0:0]"/>
|
||||||
input mux + the crossbar in Stratix IV is 167 ps. We already have a 72 ps
|
<direct name="direct3" input="fle.clk" output="ble6.clk"/>
|
||||||
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[9:0].out" output="fle[9:0].in">
|
|
||||||
<delay_constant max="95e-12" in_port="clb.I" out_port="fle[9:0].in"/>
|
|
||||||
<delay_constant max="75e-12" in_port="fle[9:0].out" out_port="fle[9:0].in"/>
|
|
||||||
</complete>
|
|
||||||
<complete name="clks" input="clb.clk" output="fle[9:0].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[9:0].out" output="clb.O"/>
|
|
||||||
</interconnect>
|
</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 -->
|
</mode>
|
||||||
<!-- Place this general purpose logic block in any unspecified column -->
|
<!-- 6-LUT mode definition end -->
|
||||||
</pb_type>
|
</pb_type>
|
||||||
<!-- Define general purpose logic block (CLB) ends -->
|
<interconnect>
|
||||||
</complexblocklist>
|
<complete name="crossbar" input="clb.I fle[9:0].out" output="fle[9:0].in">
|
||||||
|
<delay_constant max="95e-12" in_port="clb.I" out_port="fle[9:0].in"/>
|
||||||
|
<delay_constant max="75e-12" in_port="fle[9:0].out" out_port="fle[9:0].in"/>
|
||||||
|
</complete>
|
||||||
|
<complete name="clks" input="clb.clk" output="fle[9:0].clk">
|
||||||
|
</complete>
|
||||||
|
<direct name="clbouts1" input="fle[9:0].out" output="clb.O"/>
|
||||||
|
</interconnect>
|
||||||
|
</pb_type>
|
||||||
|
</complexblocklist>
|
||||||
</architecture>
|
</architecture>
|
|
@ -13,8 +13,6 @@ power_analysis = false
|
||||||
spice_output=false
|
spice_output=false
|
||||||
verilog_output=true
|
verilog_output=true
|
||||||
timeout_each_job = 20*60
|
timeout_each_job = 20*60
|
||||||
# fpga_flow= vpr_blif If input in in .blif format
|
|
||||||
# fpga_flow= yosys_vpr If input in in .v format
|
|
||||||
fpga_flow=yosys_vpr
|
fpga_flow=yosys_vpr
|
||||||
|
|
||||||
[OpenFPGA_SHELL]
|
[OpenFPGA_SHELL]
|
||||||
|
@ -26,7 +24,7 @@ openfpga_sim_setting_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_simulatio
|
||||||
arch0=${PATH:TASK_DIR}/arch/vpr_arch.xml
|
arch0=${PATH:TASK_DIR}/arch/vpr_arch.xml
|
||||||
|
|
||||||
[BENCHMARKS]
|
[BENCHMARKS]
|
||||||
# bench0=${PATH:TASK_DIR}/micro_benchmark/and2/and2.blif
|
bench0=${PATH:TASK_DIR}/micro_benchmark/and2/and2.v
|
||||||
bench1=${PATH:TASK_DIR}/micro_benchmark/mult8/mult8.v
|
bench1=${PATH:TASK_DIR}/micro_benchmark/mult8/mult8.v
|
||||||
|
|
||||||
[SYNTHESIS_PARAM]
|
[SYNTHESIS_PARAM]
|
||||||
|
@ -35,7 +33,6 @@ bench_read_verilog_options_common = -nolatches
|
||||||
bench_yosys_common=${PATH:OPENFPGA_PATH}/openfpga_flow/misc/ys_tmpl_yosys_vpr_flow.ys
|
bench_yosys_common=${PATH:OPENFPGA_PATH}/openfpga_flow/misc/ys_tmpl_yosys_vpr_flow.ys
|
||||||
|
|
||||||
bench0_top = and2
|
bench0_top = and2
|
||||||
bench0_act = ${PATH:TASK_DIR}/micro_benchmark/and2/and2.act
|
|
||||||
bench0_verilog = ${PATH:TASK_DIR}/micro_benchmark/and2/and2.v
|
bench0_verilog = ${PATH:TASK_DIR}/micro_benchmark/and2/and2.v
|
||||||
bench1_top = mult8
|
bench1_top = mult8
|
||||||
bench1_verilog = ${PATH:TASK_DIR}/micro_benchmark/mult8/mult8.v
|
bench1_verilog = ${PATH:TASK_DIR}/micro_benchmark/mult8/mult8.v
|
||||||
|
|
|
@ -44,6 +44,7 @@ build_fabric_bitstream --verbose
|
||||||
|
|
||||||
# Write fabric-dependent bitstream
|
# Write fabric-dependent bitstream
|
||||||
write_fabric_bitstream --file fabric_bitstream.bit --format plain_text
|
write_fabric_bitstream --file fabric_bitstream.bit --format plain_text
|
||||||
|
write_fabric_bitstream --file fabric_bitstream.xml --format xml
|
||||||
|
|
||||||
# Write the Verilog netlist for FPGA fabric
|
# Write the Verilog netlist for FPGA fabric
|
||||||
# - Enable the use of explicit port mapping in Verilog netlist
|
# - Enable the use of explicit port mapping in Verilog netlist
|
||||||
|
|
Loading…
Reference in New Issue