Merge branch 'dev' into ganesh_dev

.travis/script.sh

@@ -18,6 +18,11 @@ end_section "OpenFPGA.build"
 
 start_section "OpenFPGA.TaskTun" "${GREEN}..Running_Regression..${NC}"
 cd -
+
+###############################################
+# OpenFPGA with VPR7
+# TO BE DEPRECATED
+##############################################
 echo -e "Testing single-mode architectures";
 python3 openfpga_flow/scripts/run_fpga_task.py single_mode --debug --show_thread_logs
 #python3 openfpga_flow/scripts/run_fpga_task.py s298 
@@ -37,4 +42,58 @@ python3 openfpga_flow/scripts/run_fpga_task.py explicit_verilog --debug --show_t
 echo -e "Testing Verilog generation with grid pin duplication ";
 python3 openfpga_flow/scripts/run_fpga_task.py duplicate_grid_pin --debug --show_thread_logs
 
+###############################################
+# OpenFPGA Shell with VPR8
+# (Will replace all the old tests)
+##############################################
+echo -e "Testing OpenFPGA Shell";
+
+echo -e "Testing Verilog generation with simple fracturable LUT6 ";
+python3 openfpga_flow/scripts/run_fpga_task.py openfpga_shell/frac_lut --debug --show_thread_logs
+
+echo -e "Testing Verilog generation with VPR's untileable routing architecture ";
+python3 openfpga_flow/scripts/run_fpga_task.py openfpga_shell/untileable --debug --show_thread_logs
+
+echo -e "Testing Verilog generation with hard adder chain in CLBs ";
+python3 openfpga_flow/scripts/run_fpga_task.py openfpga_shell/hard_adder --debug --show_thread_logs
+
+echo -e "Testing Verilog generation with 16k block RAMs ";
+python3 openfpga_flow/scripts/run_fpga_task.py openfpga_shell/bram/dpram16k --debug --show_thread_logs
+
+echo -e "Testing Verilog generation with 16k block RAMs spanning two columns ";
+python3 openfpga_flow/scripts/run_fpga_task.py openfpga_shell/bram/wide_dpram16k --debug --show_thread_logs
+
+echo -e "Testing Verilog generation with different I/O capacities on each side of an FPGA ";
+python3 openfpga_flow/scripts/run_fpga_task.py openfpga_shell/io/multi_io_capacity --debug --show_thread_logs
+
+echo -e "Testing Verilog generation with I/Os only on left and right sides of an FPGA ";
+python3 openfpga_flow/scripts/run_fpga_task.py openfpga_shell/io/reduced_io --debug --show_thread_logs
+
+echo -e "Testing Verilog generation with adder chain across an FPGA";
+python3 openfpga_flow/scripts/run_fpga_task.py openfpga_shell/fabric_chain/adder_chain --debug --show_thread_logs
+
+echo -e "Testing Verilog generation with shift register chain across an FPGA";
+python3 openfpga_flow/scripts/run_fpga_task.py openfpga_shell/fabric_chain/register_chain --debug --show_thread_logs
+
+echo -e "Testing Verilog generation with scan chain across an FPGA";
+python3 openfpga_flow/scripts/run_fpga_task.py openfpga_shell/fabric_chain/scan_chain --debug --show_thread_logs
+
+echo -e "Testing Verilog generation with routing mutliplexers implemented by tree structure";
+python3 openfpga_flow/scripts/run_fpga_task.py openfpga_shell/mux_design/tree_structure --debug --show_thread_logs
+
+echo -e "Testing Verilog generation with routing mutliplexers implemented by standard cell MUX2";
+python3 openfpga_flow/scripts/run_fpga_task.py openfpga_shell/mux_design/stdcell_mux2 --debug --show_thread_logs
+
+echo -e "Testing Verilog generation with behavioral description";
+python3 openfpga_flow/scripts/run_fpga_task.py openfpga_shell/behavioral_verilog --debug --show_thread_logs
+
+echo -e "Testing implicit Verilog generation";
+python3 openfpga_flow/scripts/run_fpga_task.py openfpga_shell/implicit_verilog --debug --show_thread_logs
+
+echo -e "Testing Verilog generation with flatten routing modules";
+python3 openfpga_flow/scripts/run_fpga_task.py openfpga_shell/flatten_routing --debug --show_thread_logs
+
+echo -e "Testing Verilog generation with duplicated grid output pins";
+python3 openfpga_flow/scripts/run_fpga_task.py openfpga_shell/duplicated_grid_pin --debug --show_thread_logs
+
 end_section "OpenFPGA.TaskTun"

libopenfpga/libopenfpgashell/src/shell.tpp

@@ -311,9 +311,9 @@ void Shell<T>::run_script_mode(const char* script_file_name, T& context) {
     /* Remove the space at the end of the line
      * So that we can check easily if there is a continued line in the end  
      */
-    cmd_part.erase(std::find_if(cmd_part.rbegin(), cmd_part.rend(), [](int ch) {
-      return !std::isspace(ch);
-    }).base(), cmd_part.end());
+    StringToken cmd_part_tokenizer(cmd_part);
+    cmd_part_tokenizer.rtrim(std::string(" "));
+    cmd_part = cmd_part_tokenizer.data();
 
     /* If the line ends with '\', this is a continued line, parse the next until it ends */
     if ('\\' == cmd_part.back()) {
@@ -334,9 +334,9 @@ void Shell<T>::run_script_mode(const char* script_file_name, T& context) {
     }
 
     /* Remove the space at the beginning of the line */
-    cmd_line.erase(cmd_line.begin(), std::find_if(cmd_line.begin(), cmd_line.end(), [](int ch) {
-      return !std::isspace(ch);
-    }));
+    StringToken cmd_line_tokenizer(cmd_line);
+    cmd_line_tokenizer.ltrim(std::string(" "));
+    cmd_line = cmd_line_tokenizer.data();
 
     /* Process the command only when the full command line in ended */
     if (!cmd_line.empty()) {

openfpga/src/fabric/build_grid_modules.cpp

@@ -289,6 +289,7 @@ void build_primitive_block_module(ModuleManager& module_manager,
     /* Record memory-related information */
     module_manager.add_configurable_child(primitive_module, memory_module, memory_instance_id);
   }
+
   /* Add all the nets to connect configuration ports from memory module to primitive modules
    * This is a one-shot addition that covers all the memory modules in this primitive module!
    */

openfpga/test_script/and_k6_frac_tileable_adder_chain.openfpga

@@ -41,7 +41,9 @@ build_fabric_bitstream --verbose
 
 # Write the Verilog netlist for FPGA fabric
 #  - Enable the use of explicit port mapping in Verilog netlist
-write_fabric_verilog --file /var/tmp/xtang/openfpga_test_src/SRC --explicit_port_mapping --include_timing --include_signal_init --support_icarus_simulator --print_user_defined_template --verbose
+ write_fabric_verilog --file /var/tmp/xtang/openfpga_test_src/SRC \
+  --explicit_port_mapping --include_timing --include_signal_init \
+  --support_icarus_simulator --print_user_defined_template --verbose
 
 # Write the Verilog testbench for FPGA fabric
 #  - We suggest the use of same output directory as fabric Verilog netlists

openfpga_flow/OpenFPGAShellScripts/duplicated_grid_pin_example_script.openfpga

@@ -0,0 +1,61 @@
+# Run VPR for the 'and' design
+#--write_rr_graph example_rr_graph.xml
+vpr ${VPR_ARCH_FILE} ${VPR_TESTBENCH_BLIF} --clock_modeling route
+
+# Read OpenFPGA architecture definition
+read_openfpga_arch -f ${OPENFPGA_ARCH_FILE}
+
+# Annotate the OpenFPGA architecture to VPR data base
+# to debug use --verbose options
+link_openfpga_arch --activity_file ${ACTIVITY_FILE} --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
+build_fabric --compress_routing #--verbose
+
+# 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 #--verbose
+
+# Build the bitstream
+#  - Output the fabric-independent bitstream to a file
+build_architecture_bitstream --verbose --file fabric_indepenent_bitstream.xml
+
+# Build fabric-dependent bitstream
+build_fabric_bitstream --verbose
+
+# Write the Verilog netlist for FPGA fabric
+#  - Enable the use of explicit port mapping in Verilog netlist
+write_fabric_verilog --file ./SRC --explicit_port_mapping --include_timing --include_signal_init --support_icarus_simulator --print_user_defined_template --verbose
+
+# Write the Verilog testbench for FPGA fabric
+#  - We suggest the use of same output directory as fabric Verilog netlists
+#  - Must specify the reference benchmark file if you want to output any testbenches
+#  - Enable top-level testbench which is a full verification including programming circuit and core logic of FPGA
+#  - Enable pre-configured top-level testbench which is a fast verification skipping programming phase
+#  - Simulation ini file is optional and is needed only when you need to interface different HDL simulators using openfpga flow-run scripts
+write_verilog_testbench --file ./SRC --reference_benchmark_file_path ${REFERENCE_VERILOG_TESTBENCH} --print_top_testbench --print_preconfig_top_testbench --print_simulation_ini ./SimulationDeck/simulation_deck.ini
+
+# Write the SDC files for PnR backend
+#  - Turn on every options here
+write_pnr_sdc --file ./SDC
+
+# Write the SDC to run timing analysis for a mapped FPGA fabric
+write_analysis_sdc --file ./SDC_analysis
+
+# Finish and exit OpenFPGA
+exit
+
+# Note :
+# To run verification at the end of the flow maintain source in ./SRC directory

openfpga_flow/OpenFPGAShellScripts/example_script.openfpga

@@ -21,7 +21,7 @@ lut_truth_table_fixup
 # Build the module graph
 #  - Enabled compression on routing architecture modules
 #  - Enable pin duplication on grid modules
-build_fabric --compress_routing --duplicate_grid_pin #--verbose
+build_fabric --compress_routing #--verbose
 
 # Repack the netlist to physical pbs
 # This must be done before bitstream generator and testbench generation
@@ -58,4 +58,4 @@ write_analysis_sdc --file ./SDC_analysis
 exit
 
 # Note :
-# To run verification at the end of the flow maintain source in ./SRC directory
+# To run verification at the end of the flow maintain source in ./SRC directory

openfpga_flow/OpenFPGAShellScripts/flatten_routing_example_script.openfpga

@@ -0,0 +1,61 @@
+# Run VPR for the 'and' design
+#--write_rr_graph example_rr_graph.xml
+vpr ${VPR_ARCH_FILE} ${VPR_TESTBENCH_BLIF} --clock_modeling route
+
+# Read OpenFPGA architecture definition
+read_openfpga_arch -f ${OPENFPGA_ARCH_FILE}
+
+# Annotate the OpenFPGA architecture to VPR data base
+# to debug use --verbose options
+link_openfpga_arch --activity_file ${ACTIVITY_FILE}
+
+# 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
+build_fabric #--verbose
+
+# 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 #--verbose
+
+# Build the bitstream
+#  - Output the fabric-independent bitstream to a file
+build_architecture_bitstream --verbose --file fabric_indepenent_bitstream.xml
+
+# Build fabric-dependent bitstream
+build_fabric_bitstream --verbose
+
+# Write the Verilog netlist for FPGA fabric
+#  - Enable the use of explicit port mapping in Verilog netlist
+write_fabric_verilog --file ./SRC --explicit_port_mapping --include_timing --include_signal_init --support_icarus_simulator --print_user_defined_template --verbose
+
+# Write the Verilog testbench for FPGA fabric
+#  - We suggest the use of same output directory as fabric Verilog netlists
+#  - Must specify the reference benchmark file if you want to output any testbenches
+#  - Enable top-level testbench which is a full verification including programming circuit and core logic of FPGA
+#  - Enable pre-configured top-level testbench which is a fast verification skipping programming phase
+#  - Simulation ini file is optional and is needed only when you need to interface different HDL simulators using openfpga flow-run scripts
+write_verilog_testbench --file ./SRC --reference_benchmark_file_path ${REFERENCE_VERILOG_TESTBENCH} --print_top_testbench --print_preconfig_top_testbench --print_simulation_ini ./SimulationDeck/simulation_deck.ini
+
+# Write the SDC files for PnR backend
+#  - Turn on every options here
+write_pnr_sdc --file ./SDC
+
+# Write the SDC to run timing analysis for a mapped FPGA fabric
+write_analysis_sdc --file ./SDC_analysis
+
+# Finish and exit OpenFPGA
+exit
+
+# Note :
+# To run verification at the end of the flow maintain source in ./SRC directory

openfpga_flow/OpenFPGAShellScripts/implicit_verilog_example_script.openfpga

@@ -0,0 +1,61 @@
+# Run VPR for the 'and' design
+#--write_rr_graph example_rr_graph.xml
+vpr ${VPR_ARCH_FILE} ${VPR_TESTBENCH_BLIF} --clock_modeling route
+
+# Read OpenFPGA architecture definition
+read_openfpga_arch -f ${OPENFPGA_ARCH_FILE}
+
+# Annotate the OpenFPGA architecture to VPR data base
+# to debug use --verbose options
+link_openfpga_arch --activity_file ${ACTIVITY_FILE} --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
+build_fabric --compress_routing --duplicate_grid_pin #--verbose
+
+# 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 #--verbose
+
+# Build the bitstream
+#  - Output the fabric-independent bitstream to a file
+build_architecture_bitstream --verbose --file fabric_indepenent_bitstream.xml
+
+# Build fabric-dependent bitstream
+build_fabric_bitstream --verbose
+
+# Write the Verilog netlist for FPGA fabric
+#  - Enable the use of explicit port mapping in Verilog netlist
+write_fabric_verilog --file ./SRC --include_timing --include_signal_init --support_icarus_simulator --print_user_defined_template --verbose
+
+# Write the Verilog testbench for FPGA fabric
+#  - We suggest the use of same output directory as fabric Verilog netlists
+#  - Must specify the reference benchmark file if you want to output any testbenches
+#  - Enable top-level testbench which is a full verification including programming circuit and core logic of FPGA
+#  - Enable pre-configured top-level testbench which is a fast verification skipping programming phase
+#  - Simulation ini file is optional and is needed only when you need to interface different HDL simulators using openfpga flow-run scripts
+write_verilog_testbench --file ./SRC --reference_benchmark_file_path ${REFERENCE_VERILOG_TESTBENCH} --print_top_testbench --print_preconfig_top_testbench --print_simulation_ini ./SimulationDeck/simulation_deck.ini
+
+# Write the SDC files for PnR backend
+#  - Turn on every options here
+write_pnr_sdc --file ./SDC
+
+# Write the SDC to run timing analysis for a mapped FPGA fabric
+write_analysis_sdc --file ./SDC_analysis
+
+# Finish and exit OpenFPGA
+exit
+
+# Note :
+# To run verification at the end of the flow maintain source in ./SRC directory

openfpga_flow/VerilogNetlists/aib.v

@@ -0,0 +1,19 @@
+//-----------------------------------------------------
+// Design Name : AIB interface
+// File Name   : aib.v
+// Function    : A wrapper for AIB interface
+// Coder       : Xifan Tang
+//-----------------------------------------------------
+
+module aib (
+	input tx_clk,
+	input rx_clk,
+	inout[0:79] pad,
+	input[0:79] tx_data,
+	output[0:79] rx_data);
+
+// May add the logic function of a real AIB
+// Refer to the offical AIB github
+//   https://github.com/intel/aib-phy-hardware
+
+endmodule

openfpga_flow/VerilogNetlists/dpram16k.v

@@ -0,0 +1,56 @@
+//-----------------------------------------------------
+// Design Name : dual_port_ram
+// File Name   : dpram.v
+// Function    : Dual port RAM 32x1024 
+// Coder       : Aurelien
+//-----------------------------------------------------
+
+module dpram_512x32 (
+	input clk,
+	input wen,
+	input ren,
+	input[0:9] waddr,
+	input[0:9] raddr,
+	input[0:31] d_in,
+	output[0:31] d_out );
+
+		dual_port_sram memory_0 (
+			.wclk		(clk),
+			.wen		(wen),
+			.waddr		(waddr),
+			.data_in	(d_in),
+			.rclk		(clk),
+			.ren		(ren),
+			.raddr		(raddr),
+			.d_out		(d_out) );
+
+endmodule
+
+module dual_port_sram (
+	input wclk,
+	input wen,
+	input[0:9] waddr,
+	input[0:31] data_in,
+	input rclk,
+	input ren,
+	input[0:9] raddr,
+	output[0:31] d_out );
+
+	reg[0:31] ram[0:1023];
+	reg[0:31] internal;
+
+	assign d_out = internal;
+
+	always @(posedge wclk) begin
+		if(wen) begin
+			ram[waddr] <= data_in;
+		end
+	end
+
+	always @(posedge rclk) begin
+		if(ren) begin
+			internal <= ram[raddr];
+		end
+	end
+
+endmodule

openfpga_flow/VerilogNetlists/ff.v

@@ -33,6 +33,38 @@ assign Q = q_reg;
 
 endmodule //End Of Module static_dff
 
+module scan_chain_ff (
+/* Global ports go first */
+input set,     // set input
+input reset, // Reset input
+input clk, // Clock Input
+input TESTEN, // Clock Input
+/* Local ports follow */
+input D, // Data Input
+input DI, // Scan Chain Data Input
+output Q // Q output
+);
+//------------Internal Variables--------
+reg q_reg;
+
+//-------------Code Starts Here---------
+always @ ( posedge clk or posedge reset or posedge set)
+if (reset) begin
+  q_reg <= 1'b0;
+end else if (set) begin
+  q_reg <= 1'b1;
+end else if (TESTEN) begin
+  q_reg <= DI;
+end else begin
+  q_reg <= D;
+end
+
+// Wire q_reg to Q
+assign Q = q_reg;
+
+endmodule //End Of Module static_dff
+
+
 //-----------------------------------------------------
 // Design Name : scan_chain_dff
 // File Name   : ff.v

openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_adder_chain_40nm.xml

@@ -161,7 +161,7 @@
   <!-- Physical descriptions begin -->
   <layout tileable="true">
     <!--auto_layout aspect_ratio="1.0"-->
-    <fixed_layout name="4x4" width="6" height="6">
+    <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"/>

openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_adder_chain_mem16K_40nm.xml

@@ -195,7 +195,7 @@
   <!-- Physical descriptions begin -->
   <layout tileable="true" through_channel="false">
     <!--auto_layout aspect_ratio="1.0"-->
-    <fixed_layout name="4x4" width="5" height="4">
+    <fixed_layout name="3x2" width="5" height="4">
       <!--Perimeter of 'io' blocks with 'EMPTY' blocks at corners-->
       <perimeter type="io" priority="100"/>
       <corners type="EMPTY" priority="101"/>

openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_adder_chain_mem16K_aib_40nm.xml

@@ -225,7 +225,7 @@
   <!-- Physical descriptions begin -->
   <layout tileable="true" through_channel="false">
     <!--auto_layout aspect_ratio="1.0"-->
-    <fixed_layout name="4x4" width="7" height="6">
+    <fixed_layout name="3x4" width="5" height="6">
       <!--Perimeter of 'io' blocks with 'EMPTY' blocks at corners-->
       <perimeter type="io" priority="10"/>
       <corners type="EMPTY" priority="101"/>
@@ -235,7 +235,7 @@
       <col type="memory" startx="2" starty="1" repeatx="8" priority="20"/>
       <col type="EMPTY" startx="2" repeatx="8" starty="1" priority="19"/>
       <!-- Single instance of an AIB interface -->
-      <single type="aib" x="6" y="1" priority="20"/>
+      <single type="aib" x="4" y="1" priority="20"/>
     </fixed_layout>
     <!-- /auto_layout -->
   </layout>

openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_adder_chain_mem16K_multi_io_capacity_40nm.xml

@@ -226,7 +226,7 @@
   <!-- Physical descriptions begin -->
   <layout tileable="true" through_channel="false">
     <!--auto_layout aspect_ratio="1.0"-->
-    <fixed_layout name="4x4" width="5" height="4">
+    <fixed_layout name="3x2" width="5" height="4">
       <!--Perimeter of 'io' blocks with 'EMPTY' blocks at corners-->
       <row type="io_top" starty="H-1" priority="100"/>
       <row type="io_bottom" starty="0" priority="100"/>

openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_adder_chain_mem16K_reduced_io_40nm.xml

@@ -195,7 +195,7 @@
   <!-- Physical descriptions begin -->
   <layout tileable="true" through_channel="false">
     <!--auto_layout aspect_ratio="1.0"-->
-    <fixed_layout name="4x4" width="7" height="6">
+    <fixed_layout name="3x2" width="5" height="4">
       <!--Perimeter of 'io' blocks with 'EMPTY' blocks at corners-->
       <perimeter type="io" priority="10"/>
       <corners type="EMPTY" priority="101"/>

openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_adder_register_chain_40nm.xml

@@ -0,0 +1,696 @@
+<!-- 
+  Flagship Heterogeneous Architecture with Carry Chains for VTR 7.0.
+
+  - 40 nm technology
+  - General purpose logic block: 
+    K = 6, N = 10, fracturable 6 LUTs (can operate as one 6-LUT or two 5-LUTs with 8 total FLE inputs (2 inputs of which are shared by the 5-LUTs) 
+    with optionally registered outputs
+    Each 5-LUT has an arithemtic mode that converts it to a single-bit adder with both inputs driven by 4-LUTs (both 4-LUTs share all 4 inputs)
+    Carry chain links to vertically adjacent logic blocks
+  - Memory size 32 Kbits, memory aspect ratios vary from a data width of 1 to data width of 64.  
+    Height = 6, found on every (8n+2)th column
+  - Multiplier modes: one 36x36, two 18x18, each 18x18 can also operate as two 9x9.  
+    Height = 4, found on every (8n+6)th column
+  - Routing architecture: L = 4, fc_in = 0.15, Fc_out = 0.1
+
+  Details on Modelling:
+
+  The electrical design of the architecture described here is NOT from an 
+  optimized, SPICED architecture.  Instead, we attempt to create a reasonable 
+  architecture file by using an existing commercial FPGA to approximate the area, 
+  delay, and power of the underlying components. This is combined with a reasonable 40 nm 
+  model of wiring and circuit design for low-level routing components, where available.
+  The resulting architecture has delays that roughly match a commercial 40 nm FPGA, but also 
+  has wiring electrical parameters that allow the wire lengths and switch patterns to be 
+  modified and you will still get reasonable delay results for the new architecture.
+  The following describes, in detail, how we obtained the various electrical values for this 
+  architecture.
+
+  Rmin for nmos and pmos, routing buffer sizes, and I/O pad delays are from the ifar 
+  architecture created by Ian Kuon: K06 N10 45nm fc 0.15 area-delay optimized architecture. 
+  (n10k06l04.fc15.area1delay1.cmos45nm.bptm.cmos45nm.xml)      
+  This routing architecture was optimized for 45 nm, and we have scaled it linearly to 40 nm to 
+  match the overall target (a 40 nm FPGA).
+
+  We obtain delay numbers by measuring delays of routing, soft logic blocks, 
+  memories, and multipliers from test circuits on a Stratix IV GX device 
+  (EP4SGX230DF29C2X, i.e. fastest speed grade). For routing, we took the average delay of H4 and V4 
+  wires.  Rmetal and Cmetal values for the routing wires were obtained from work done by Charles 
+  Chiasson. We use a 96 nm half-pitch (corresponding to mid-level metal stack 40 nm routing) and 
+  take the R and C data from the ITRS roadmap.  
+
+  For the general purpose logic block, we assume that the area and delays of the Stratix IV 
+  crossbar is close enough to the crossbar modelled here.  
+  Stratix IV uses 52 inputs and 20 feedback lines, but only a half-populated crossbar, leading to 
+  36:1 multiplexers.  We match these parameters in this architecture.
+
+  For LUTs, we include LUT 
+  delays measured from Stratix IV which is dependant on the input used (ie. some 
+  LUT inputs are faster than others).  The CAD tools at the time of VTR 7 does 
+  not consider differences in LUT input delays.
+
+  Adder delays obtained as approximate values from a Stratix IV EP4SE230F29C3 device.  
+  Delay obtained by compiling a 256 bit adder (registered inputs and outputs, 
+  all pins except clock virtual) then measuring the delays in chip-planner, 
+  sumout delay = 0.271ns to 0.348 ns, intra-block carry delay = 0.011 ns, 
+  inter-block carry delay = 0.327 ns.  Given this data, I will approximate 
+  sumout 0.3 ns, intra-block carry-delay = 0.01 ns, and 
+  inter-block carry-delay = 0.16 ns (since Altera inter-block carry delay has 
+  overhead that we don't have, I'll approximate the delay of a simpler chain at 
+  one half what they have.  This is very rough, anything from 0.01ns to 0.327ns 
+  can be justified).
+
+  Logic block area numbers obtained by scaling overall tile area of a 65nm 
+  Stratix III device, (as given in Wong, Betz and Rose, FPGA 2011) to 40 nm, then subtracting out 
+  routing area at a channel width of 300. We use a channel width of 300 because it can route 
+  all the VTR 6.0 benchmark circuits with an approximately 20% safety margin, and is also close to the
+  total channel width of Stratix IV. Hence this channel width is close to the commercial practice of
+  choosing a width that provides high routability. The architecture can be routed at different channel
+  widths, but we estimate the tile size and hence the physical length of routing wires assuming
+  a channel width of 300.
+
+  Sanity checks employed:
+    1.  We confirmed the routing buffer delay is ~1/3rd of total routing delay at L = 4. This matches 
+        common electrical design.
+
+
+  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>
+    <model name="adder">
+      <input_ports>
+        <port name="a" combinational_sink_ports="sumout cout"/>
+        <port name="b" combinational_sink_ports="sumout cout"/>
+        <port name="cin" combinational_sink_ports="sumout cout"/>
+      </input_ports>
+      <output_ports>
+        <port name="cout"/>
+        <port name="sumout"/>
+      </output_ports>
+    </model>
+    <!-- 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>
+    <!-- A virtual model for I/O to be used in the physical mode of io block -->
+    <model name="frac_lut6">
+      <input_ports>
+        <port name="in"/>
+      </input_ports>
+      <output_ports>
+        <port name="lut4_out"/>
+        <port name="lut5_out"/>
+        <port name="lut6_out"/>
+      </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="40" equivalent="full"/>
+      <input name="cin" num_pins="1"/>
+      <input name="regin" num_pins="1"/>
+      <output name="O" num_pins="20" equivalent="none"/>
+      <output name="cout" num_pins="1"/>
+      <output name="regout" num_pins="1"/>
+      <clock name="clk" num_pins="1"/>
+      <fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10">
+        <fc_override port_name="cin" fc_type="frac" fc_val="0"/>
+        <fc_override port_name="cout" fc_type="frac" fc_val="0"/>
+        <fc_override port_name="regin" fc_type="frac" fc_val="0"/>
+        <fc_override port_name="regout" fc_type="frac" fc_val="0"/>
+      </fc>
+      <!--  Highly recommand to customize pin location when direct connection is used!!! -->
+      <!--pinlocations pattern="spread"/-->
+      <pinlocations pattern="custom">
+        <loc side="left">clb.clk</loc>
+        <loc side="top">clb.cin clb.regin</loc>
+        <loc side="right">clb.O[9:0] clb.I[19:0]</loc>
+        <loc side="bottom">clb.cout clb.regout clb.O[19:10] clb.I[39:20]</loc>
+      </pinlocations>
+    </tile>
+  </tiles>
+  <!-- ODIN II specific config ends -->
+  <!-- Physical descriptions begin -->
+  <layout tileable="true">
+    <!--auto_layout aspect_ratio="1.0"-->
+    <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>
+    <!-- /auto_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. -->
+    <!-- GIVE a specific name for the segment! OpenFPGA appreciate that! -->
+    <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>
+  <directlist>
+    <direct name="adder_carry" from_pin="clb.cout" to_pin="clb.cin" x_offset="0" y_offset="-1" z_offset="0"/>
+    <direct name="shift_register" from_pin="clb.regout" to_pin="clb.regin" x_offset="0" y_offset="-1" z_offset="0"/>
+  </directlist>
+  <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"/>
+
+      <!-- Do NOT add clock pins to I/O here!!! VPR does not build clock network in the way that OpenFPGA can support
+           If you need to register the I/O, define clocks in the circuit models
+           These clocks can be handled in back-end
+       -->
+      <!-- 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" packable="false">
+        <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="40" equivalent="full"/>
+      <input name="cin" num_pins="1"/>
+      <input name="regin" num_pins="1"/>
+      <output name="O" num_pins="20" equivalent="none"/>
+      <output name="cout" num_pins="1"/>
+      <output name="regout" num_pins="1"/>
+      <clock name="clk" num_pins="1"/>
+      <!-- Describe fracturable logic element.  
+             Each fracturable logic element has a 6-LUT that can alternatively operate as two 5-LUTs with shared inputs. 
+             The outputs of the fracturable logic element can be optionally registered
+        -->
+      <pb_type name="fle" num_pb="10">
+        <input name="in" num_pins="6"/>
+        <input name="cin" num_pins="1"/>
+        <input name="regin" num_pins="1"/>
+        <output name="out" num_pins="2"/>
+        <output name="cout" num_pins="1"/>
+        <output name="regout" num_pins="1"/>
+        <clock name="clk" num_pins="1"/>
+        <!-- Physical mode definition begin (physical implementation of the fle) -->
+        <mode name="physical" packable="false">
+          <pb_type name="fabric" num_pb="1">
+            <input name="in" num_pins="6"/>
+            <input name="cin" num_pins="1"/>
+            <input name="regin" num_pins="1"/>
+            <output name="out" num_pins="2"/>
+            <output name="cout" num_pins="1"/>
+            <output name="regout" num_pins="1"/>
+            <clock name="clk" num_pins="1"/>
+            <pb_type name="frac_logic" num_pb="1">
+              <input name="in" num_pins="6"/>
+              <output name="lut4_out" num_pins="4"/>
+              <output name="out" num_pins="2"/>
+              <!-- Define LUT -->
+              <pb_type name="frac_lut6" blif_model=".subckt frac_lut6" num_pb="1">
+                <input name="in" num_pins="6"/>
+                <output name="lut4_out" num_pins="4"/>
+                <output name="lut5_out" num_pins="2"/>
+                <output name="lut6_out" num_pins="1"/>
+              </pb_type>
+              <interconnect>
+                <direct name="direct1" input="frac_logic.in" output="frac_lut6.in"/>
+                <direct name="direct2" input="frac_lut6.lut4_out" output="frac_logic.lut4_out"/>
+                <direct name="direct3" input="frac_lut6.lut5_out[1]" output="frac_logic.out[1]"/>
+                <!-- Xifan Tang: I use out[0] because the output of lut6 in lut6 mode is wired to the out[0] -->
+                <mux name="mux1" input="frac_lut6.lut6_out frac_lut6.lut5_out[0]" output="frac_logic.out[0]"/>
+              </interconnect>
+            </pb_type>
+            <!-- Define flip-flop -->
+            <pb_type name="ff" blif_model=".latch" num_pb="2" 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>         
+            <!-- Define adders -->
+            <pb_type name="adder" blif_model=".subckt adder" num_pb="2">
+              <input name="a" num_pins="1"/>
+              <input name="b" num_pins="1"/>
+              <input name="cin" num_pins="1"/>
+              <output name="cout" num_pins="1"/>
+              <output name="sumout" num_pins="1"/>
+              <delay_constant max="0.3e-9" in_port="adder.a" out_port="adder.sumout"/>
+              <delay_constant max="0.3e-9" in_port="adder.b" out_port="adder.sumout"/>
+              <delay_constant max="0.3e-9" in_port="adder.cin" out_port="adder.sumout"/>
+              <delay_constant max="0.3e-9" in_port="adder.a" out_port="adder.cout"/>
+              <delay_constant max="0.3e-9" in_port="adder.b" out_port="adder.cout"/>
+              <delay_constant max="0.01e-9" in_port="adder.cin" out_port="adder.cout"/>
+            </pb_type>
+            <interconnect>
+              <direct name="direct1" input="fabric.in" output="frac_logic.in"/>
+              <direct name="direct2" input="fabric.cin" output="adder[0:0].cin"/>
+              <direct name="direct3" input="adder[0:0].cout" output="adder[1:1].cin"/>
+              <direct name="direct4" input="adder[1:1].cout" output="fabric.cout"/>
+              <direct name="direct5" input="frac_logic.lut4_out[0:0]" output="adder[0:0].a"/>
+              <direct name="direct6" input="frac_logic.lut4_out[1:1]" output="adder[0:0].b"/>
+              <direct name="direct7" input="frac_logic.lut4_out[2:2]" output="adder[1:1].a"/>
+              <direct name="direct8" input="frac_logic.lut4_out[3:3]" output="adder[1:1].b"/>
+              <complete name="complete1" input="fabric.clk" output="ff[1:0].clk"/>
+              <mux name="mux1" input="adder[0].sumout frac_logic.out[0] fabric.regin" output="ff[0].D">
+                <delay_constant max="25e-12" in_port="adder[0].sumout frac_logic.out[0] fabric.regin" out_port="ff[0].D"/>
+              </mux>
+              <mux name="mux2" input="adder[1].sumout frac_logic.out[1] ff[0].Q" output="ff[1].D">
+                <delay_constant max="25e-12" in_port="adder[1].sumout frac_logic.out[1] ff[0].Q" out_port="ff[1].D"/>
+              </mux>
+              <mux name="mux3" input="adder[0].sumout ff[0].Q frac_logic.out[0]" output="fabric.out[0]">
+                <!-- LUT to output is faster than FF to output on a Stratix IV -->
+                <delay_constant max="25e-12" in_port="frac_logic.out[0]" out_port="fabric.out[0]"/>
+                <delay_constant max="45e-12" in_port="ff[0].Q" out_port="fabric.out[0]"/>
+              </mux>
+              <mux name="mux4" input="adder[1].sumout ff[1].Q frac_logic.out[1]" output="fabric.out[1]">
+                <!-- LUT to output is faster than FF to output on a Stratix IV -->
+                <delay_constant max="25e-12" in_port="frac_logic.out[1]" out_port="fabric.out[1]"/>
+                <delay_constant max="45e-12" in_port="ff[1].Q" out_port="fabric.out[1]"/>
+              </mux>
+            </interconnect>
+          </pb_type>
+          <interconnect>
+            <direct name="direct1" input="fle.in" output="fabric.in"/>
+            <direct name="direct2" input="fle.cin" output="fabric.cin"/>
+            <direct name="direct3" input="fle.regin" output="fabric.regin"/>
+            <direct name="direct4" input="fabric.out" output="fle.out"/>
+            <direct name="direct5" input="fabric.cout" output="fle.cout"/>
+            <direct name="direct6" input="fabric.regout" output="fle.regout"/>
+            <direct name="direct7" input="fle.clk" output="fabric.clk"/>
+          </interconnect>
+        </mode>
+        <!-- Physical mode definition end (physical implementation of the fle) -->
+        <!-- BEGIN fle mode of dual lut5 -->
+        <mode name="n2_lut5">
+          <pb_type name="ble5" num_pb="2">
+            <input name="in" num_pins="5"/>
+            <output name="out" num_pins="1"/>
+            <clock name="clk" num_pins="1"/>
+            <!-- Regular LUT mode -->
+            <pb_type name="lut5" blif_model=".names" num_pb="1" class="lut">
+              <input name="in" num_pins="5" port_class="lut_in"/>
+              <output name="out" num_pins="1" port_class="lut_out"/>
+              <!-- LUT timing using delay matrix -->
+              <!-- These are the physical delay inputs on a Stratix IV LUT but because VPR cannot do LUT rebalancing,
+                  we instead take the average of these numbers to get more stable results
+                82e-12
+                173e-12
+                261e-12
+                263e-12
+                398e-12
+                -->
+              <delay_matrix type="max" in_port="lut5.in" out_port="lut5.out">
+                235e-12
+                235e-12
+                235e-12
+                235e-12
+                235e-12
+              </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="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="ble5.in" output="lut5.in"/>
+              <direct name="direct2" input="lut5.out" output="ff.D">
+                <pack_pattern name="ble5" in_port="lut5.out" out_port="ff.D"/>
+              </direct>
+              <direct name="direct3" input="ble5.clk" output="ff.clk"/>
+              <mux name="mux1" input="ff.Q lut5.out" output="ble5.out">
+                <delay_constant max="25e-12" in_port="lut5.out" out_port="ble5.out"/>
+                <delay_constant max="45e-12" in_port="ff.Q" out_port="ble5.out"/>
+              </mux>
+            </interconnect>
+          </pb_type>
+          <interconnect>
+            <direct name="direct1" input="fle.in[4:0]" output="ble5[0:0].in"/>
+            <direct name="direct2" input="fle.in[4:0]" output="ble5[1:1].in"/>
+            <complete name="direct3" input="fle.clk" output="ble5.clk"/>
+            <direct name="direct4" input="ble5.out" output="fle.out"/>
+          </interconnect>
+        </mode>
+        <!-- END fle mode of dual lut5 -->
+        <!-- BEGIN arithmetic mode of dual lut4 + adders -->
+        <mode name="arithmetic">
+          <pb_type name="arithmetic" num_pb="2">
+            <input name="in" num_pins="4"/>
+            <input name="cin" num_pins="1"/>
+            <output name="out" num_pins="1"/>
+            <output name="cout" num_pins="1"/>
+            <clock name="clk" num_pins="1"/>
+            <!-- Special dual-LUT mode that drives adder only -->
+            <pb_type name="lut4" blif_model=".names" num_pb="2" 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 -->
+              <!-- These are the physical delay inputs on a Stratix IV LUT but because VPR cannot do LUT rebalancing,
+                       we instead take the average of these numbers to get more stable results
+                  82e-12
+                  173e-12
+                  261e-12
+                  263e-12
+                  -->
+              <delay_matrix type="max" in_port="lut4.in" out_port="lut4.out">
+                  195e-12
+                  195e-12
+                  195e-12
+                  195e-12
+                </delay_matrix>
+            </pb_type>
+            <pb_type name="adder" blif_model=".subckt adder" num_pb="1">
+              <input name="a" num_pins="1"/>
+              <input name="b" num_pins="1"/>
+              <input name="cin" num_pins="1"/>
+              <output name="cout" num_pins="1"/>
+              <output name="sumout" num_pins="1"/>
+              <delay_constant max="0.3e-9" in_port="adder.a" out_port="adder.sumout"/>
+              <delay_constant max="0.3e-9" in_port="adder.b" out_port="adder.sumout"/>
+              <delay_constant max="0.3e-9" in_port="adder.cin" out_port="adder.sumout"/>
+              <delay_constant max="0.3e-9" in_port="adder.a" out_port="adder.cout"/>
+              <delay_constant max="0.3e-9" in_port="adder.b" out_port="adder.cout"/>
+              <delay_constant max="0.01e-9" in_port="adder.cin" out_port="adder.cout"/>
+            </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="66e-12" port="ff.D" clock="clk"/>
+              <T_clock_to_Q max="124e-12" port="ff.Q" clock="clk"/>
+            </pb_type>
+            <interconnect>
+              <direct name="clock" input="arithmetic.clk" output="ff.clk"/>
+              <direct name="lut_in1" input="arithmetic.in[3:0]" output="lut4[0:0].in[3:0]"/>
+              <direct name="lut_in2" input="arithmetic.in[3:0]" output="lut4[1:1].in[3:0]"/>
+              <direct name="lut_to_add1" input="lut4[0:0].out" output="adder.a">
+                </direct>
+              <direct name="lut_to_add2" input="lut4[1:1].out" output="adder.b">
+                </direct>
+              <direct name="add_to_ff" input="adder.sumout" output="ff.D">
+                <pack_pattern name="chain" in_port="adder.sumout" out_port="ff.D"/>
+              </direct>
+              <direct name="carry_in" input="arithmetic.cin" output="adder.cin">
+                <pack_pattern name="chain" in_port="arithmetic.cin" out_port="adder.cin"/>
+              </direct>
+              <direct name="carry_out" input="adder.cout" output="arithmetic.cout">
+                <pack_pattern name="chain" in_port="adder.cout" out_port="arithmetic.cout"/>
+              </direct>
+              <mux name="sumout" input="ff.Q adder.sumout" output="arithmetic.out">
+                <delay_constant max="25e-12" in_port="adder.sumout" out_port="arithmetic.out"/>
+                <delay_constant max="45e-12" in_port="ff.Q" out_port="arithmetic.out"/>
+              </mux>
+            </interconnect>
+          </pb_type>
+          <interconnect>
+            <direct name="direct1" input="fle.in[3:0]" output="arithmetic[0:0].in"/>
+            <direct name="direct2" input="fle.in[3:0]" output="arithmetic[1:1].in"/>
+            <direct name="carry_in" input="fle.cin" output="arithmetic[0:0].cin">
+              <pack_pattern name="chain" in_port="fle.cin" out_port="arithmetic[0:0].cin"/>
+            </direct>
+            <direct name="carry_inter" input="arithmetic[0:0].cout" output="arithmetic[1:1].cin">
+              <pack_pattern name="chain" in_port="arithmetic[0:0].cout" out_port="arithmetic[1:1].cin"/>
+            </direct>
+            <direct name="carry_out" input="arithmetic[1:1].cout" output="fle.cout">
+              <pack_pattern name="chain" in_port="arithmetic.cout" out_port="fle.cout"/>
+            </direct>
+            <complete name="direct3" input="fle.clk" output="arithmetic.clk"/>
+            <direct name="direct4" input="arithmetic.out" output="fle.out"/>
+          </interconnect>
+        </mode>
+        <!-- n2_lut5 -->
+        <mode name="n1_lut6">
+          <pb_type name="ble6" num_pb="1">
+            <input name="in" num_pins="6"/>
+            <output name="out" num_pins="1"/>
+            <clock name="clk" num_pins="1"/>
+            <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 -->
+              <!-- These are the physical delay inputs on a Stratix IV LUT but because VPR cannot do LUT rebalancing,
+                       we instead take the average of these numbers to get more stable results
+                  82e-12
+                  173e-12
+                  261e-12
+                  263e-12
+                  398e-12
+                  397e-12
+                  -->
+              <delay_matrix type="max" in_port="lut6.in" out_port="lut6.out">
+                  261e-12
+                  261e-12
+                  261e-12
+                  261e-12
+                  261e-12
+                  261e-12
+                </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="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">
+                <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">
+                <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[5:0]" 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>
+        <!-- Define n1_lut6 end -->
+        <!-- Define shift register begin -->
+        <mode name="shift_register">
+          <pb_type name="shift_reg" num_pb="1">
+            <input name="regin" num_pins="1"/>
+            <output name="regout" num_pins="1"/>
+            <clock name="clk" num_pins="1"/>
+            <pb_type name="ff" blif_model=".latch" num_pb="2" 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="shift_reg.regin" output="ff[0].D"/>
+              <direct name="direct2" input="ff[0].Q" output="ff[1].D"/>
+              <direct name="direct3" input="ff[1].Q" output="shift_reg.regout"/>
+              <complete name="complete1" input="shift_reg.clk" output="ff.clk"/>
+            </interconnect>
+          </pb_type>
+          <interconnect>
+            <direct name="direct1" input="fle.regin" output="shift_reg.regin"/>
+            <direct name="direct2" input="shift_reg.regout" output="fle.regout"/>
+            <direct name="direct3" input="fle.clk" output="shift_reg.clk"/>
+          </interconnect>
+        </mode>
+        <!-- Define shift register end --> 
+      </pb_type>
+      <interconnect>
+        <!-- We use a 50% depop crossbar built using small full xbars to get sets of logically equivalent pins 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[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[0:0]" output="clb.O[9:0]"/>
+        <direct name="clbouts2" input="fle[9:0].out[1:1]" output="clb.O[19:10]"/>
+        <!-- Carry chain links -->
+        <direct name="carry_in" input="clb.cin" output="fle[0:0].cin">
+          <!-- Put all inter-block carry chain delay on this one edge -->
+          <delay_constant max="0.16e-9" in_port="clb.cin" out_port="fle[0:0].cin"/>
+          <pack_pattern name="chain" in_port="clb.cin" out_port="fle[0:0].cin"/>
+        </direct>
+        <direct name="carry_out" input="fle[9:9].cout" output="clb.cout">
+          <pack_pattern name="chain" in_port="fle[9:9].cout" out_port="clb.cout"/>
+        </direct>
+        <direct name="carry_link" input="fle[8:0].cout" output="fle[9:1].cin">
+          <pack_pattern name="chain" in_port="fle[8:0].cout" out_port="fle[9:1].cin"/>
+        </direct>
+        <!-- Shift register chain links -->
+        <direct name="shift_register_in" input="clb.regin" output="fle[0:0].regin">
+          <!-- Put all inter-block carry chain delay on this one edge -->
+          <delay_constant max="0.16e-9" in_port="clb.regin" out_port="fle[0:0].regin"/>
+          <pack_pattern name="chain" in_port="clb.regin" out_port="fle[0:0].regin"/>
+        </direct>
+        <direct name="shift_register_out" input="fle[9:9].regout" output="clb.regout">
+          <pack_pattern name="chain" in_port="fle[9:9].regout" out_port="clb.regout"/>
+        </direct>
+        <direct name="shift_register_link" input="fle[8:0].regout" output="fle[9:1].regin">
+          <pack_pattern name="chain" in_port="fle[8:0].regout" out_port="fle[9:1].regin"/>
+        </direct>
+      </interconnect>
+    </pb_type>
+    <!-- Define general purpose logic block (CLB) ends -->
+  </complexblocklist>
+</architecture>

openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_adder_register_scan_chain_40nm.xml

@@ -0,0 +1,734 @@
+<!-- 
+  Flagship Heterogeneous Architecture with Carry Chains for VTR 7.0.
+
+  - 40 nm technology
+  - General purpose logic block: 
+    K = 6, N = 10, fracturable 6 LUTs (can operate as one 6-LUT or two 5-LUTs with 8 total FLE inputs (2 inputs of which are shared by the 5-LUTs) 
+    with optionally registered outputs
+    Each 5-LUT has an arithemtic mode that converts it to a single-bit adder with both inputs driven by 4-LUTs (both 4-LUTs share all 4 inputs)
+    Carry chain links to vertically adjacent logic blocks
+  - Memory size 32 Kbits, memory aspect ratios vary from a data width of 1 to data width of 64.  
+    Height = 6, found on every (8n+2)th column
+  - Multiplier modes: one 36x36, two 18x18, each 18x18 can also operate as two 9x9.  
+    Height = 4, found on every (8n+6)th column
+  - Routing architecture: L = 4, fc_in = 0.15, Fc_out = 0.1
+
+  Details on Modelling:
+
+  The electrical design of the architecture described here is NOT from an 
+  optimized, SPICED architecture.  Instead, we attempt to create a reasonable 
+  architecture file by using an existing commercial FPGA to approximate the area, 
+  delay, and power of the underlying components. This is combined with a reasonable 40 nm 
+  model of wiring and circuit design for low-level routing components, where available.
+  The resulting architecture has delays that roughly match a commercial 40 nm FPGA, but also 
+  has wiring electrical parameters that allow the wire lengths and switch patterns to be 
+  modified and you will still get reasonable delay results for the new architecture.
+  The following describes, in detail, how we obtained the various electrical values for this 
+  architecture.
+
+  Rmin for nmos and pmos, routing buffer sizes, and I/O pad delays are from the ifar 
+  architecture created by Ian Kuon: K06 N10 45nm fc 0.15 area-delay optimized architecture. 
+  (n10k06l04.fc15.area1delay1.cmos45nm.bptm.cmos45nm.xml)      
+  This routing architecture was optimized for 45 nm, and we have scaled it linearly to 40 nm to 
+  match the overall target (a 40 nm FPGA).
+
+  We obtain delay numbers by measuring delays of routing, soft logic blocks, 
+  memories, and multipliers from test circuits on a Stratix IV GX device 
+  (EP4SGX230DF29C2X, i.e. fastest speed grade). For routing, we took the average delay of H4 and V4 
+  wires.  Rmetal and Cmetal values for the routing wires were obtained from work done by Charles 
+  Chiasson. We use a 96 nm half-pitch (corresponding to mid-level metal stack 40 nm routing) and 
+  take the R and C data from the ITRS roadmap.  
+
+  For the general purpose logic block, we assume that the area and delays of the Stratix IV 
+  crossbar is close enough to the crossbar modelled here.  
+  Stratix IV uses 52 inputs and 20 feedback lines, but only a half-populated crossbar, leading to 
+  36:1 multiplexers.  We match these parameters in this architecture.
+
+  For LUTs, we include LUT 
+  delays measured from Stratix IV which is dependant on the input used (ie. some 
+  LUT inputs are faster than others).  The CAD tools at the time of VTR 7 does 
+  not consider differences in LUT input delays.
+
+  Adder delays obtained as approximate values from a Stratix IV EP4SE230F29C3 device.  
+  Delay obtained by compiling a 256 bit adder (registered inputs and outputs, 
+  all pins except clock virtual) then measuring the delays in chip-planner, 
+  sumout delay = 0.271ns to 0.348 ns, intra-block carry delay = 0.011 ns, 
+  inter-block carry delay = 0.327 ns.  Given this data, I will approximate 
+  sumout 0.3 ns, intra-block carry-delay = 0.01 ns, and 
+  inter-block carry-delay = 0.16 ns (since Altera inter-block carry delay has 
+  overhead that we don't have, I'll approximate the delay of a simpler chain at 
+  one half what they have.  This is very rough, anything from 0.01ns to 0.327ns 
+  can be justified).
+
+  Logic block area numbers obtained by scaling overall tile area of a 65nm 
+  Stratix III device, (as given in Wong, Betz and Rose, FPGA 2011) to 40 nm, then subtracting out 
+  routing area at a channel width of 300. We use a channel width of 300 because it can route 
+  all the VTR 6.0 benchmark circuits with an approximately 20% safety margin, and is also close to the
+  total channel width of Stratix IV. Hence this channel width is close to the commercial practice of
+  choosing a width that provides high routability. The architecture can be routed at different channel
+  widths, but we estimate the tile size and hence the physical length of routing wires assuming
+  a channel width of 300.
+
+  Sanity checks employed:
+    1.  We confirmed the routing buffer delay is ~1/3rd of total routing delay at L = 4. This matches 
+        common electrical design.
+
+
+  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>
+    <model name="adder">
+      <input_ports>
+        <port name="a" combinational_sink_ports="sumout cout"/>
+        <port name="b" combinational_sink_ports="sumout cout"/>
+        <port name="cin" combinational_sink_ports="sumout cout"/>
+      </input_ports>
+      <output_ports>
+        <port name="cout"/>
+        <port name="sumout"/>
+      </output_ports>
+    </model>
+    <!-- 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>
+    <!-- A virtual model for fractruable LUT to be used in the physical mode of LUT -->
+    <model name="frac_lut6">
+      <input_ports>
+        <port name="in"/>
+      </input_ports>
+      <output_ports>
+        <port name="lut4_out"/>
+        <port name="lut5_out"/>
+        <port name="lut6_out"/>
+      </output_ports>
+    </model>
+    <!-- A virtual model for scan-chain flip-flop to be used in the physical mode of FF -->
+    <model name="scff">
+      <input_ports>
+        <port name="D" clock="clk"/>
+        <port name="DI" clock="clk"/>
+        <port name="clk" is_clock="1"/>
+      </input_ports>
+      <output_ports>
+        <port name="Q" clock="clk"/>
+      </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="40" equivalent="full"/>
+      <input name="cin" num_pins="1"/>
+      <input name="regin" num_pins="1"/>
+      <input name="scin" num_pins="1"/>
+      <output name="O" num_pins="20" equivalent="none"/>
+      <output name="cout" num_pins="1"/>
+      <output name="regout" num_pins="1"/>
+      <output name="scout" num_pins="1"/>
+      <clock name="clk" num_pins="1"/>
+      <fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10">
+        <fc_override port_name="cin" fc_type="frac" fc_val="0"/>
+        <fc_override port_name="cout" fc_type="frac" fc_val="0"/>
+        <fc_override port_name="regin" fc_type="frac" fc_val="0"/>
+        <fc_override port_name="regout" fc_type="frac" fc_val="0"/>
+        <fc_override port_name="scin" fc_type="frac" fc_val="0"/>
+        <fc_override port_name="scout" fc_type="frac" fc_val="0"/>
+      </fc>
+      <!--  Highly recommand to customize pin location when direct connection is used!!! -->
+      <!--pinlocations pattern="spread"/-->
+      <pinlocations pattern="custom">
+        <loc side="left">clb.clk</loc>
+        <loc side="top">clb.cin clb.regin clb.scin</loc>
+        <loc side="right">clb.O[9:0] clb.I[19:0]</loc>
+        <loc side="bottom">clb.cout clb.regout clb.scout clb.O[19:10] clb.I[39:20]</loc>
+      </pinlocations>
+    </tile>
+  </tiles>
+  <!-- ODIN II specific config ends -->
+  <!-- Physical descriptions begin -->
+  <layout tileable="true">
+    <!--auto_layout aspect_ratio="1.0"-->
+    <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>
+    <!-- /auto_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. -->
+    <!-- GIVE a specific name for the segment! OpenFPGA appreciate that! -->
+    <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>
+  <directlist>
+    <direct name="adder_carry" from_pin="clb.cout" to_pin="clb.cin" x_offset="0" y_offset="-1" z_offset="0"/>
+    <direct name="shift_register" from_pin="clb.regout" to_pin="clb.regin" x_offset="0" y_offset="-1" z_offset="0"/>
+    <direct name="scan_chain" from_pin="clb.scout" to_pin="clb.scin" x_offset="0" y_offset="-1" z_offset="0"/>
+  </directlist>
+  <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"/>
+
+      <!-- Do NOT add clock pins to I/O here!!! VPR does not build clock network in the way that OpenFPGA can support
+           If you need to register the I/O, define clocks in the circuit models
+           These clocks can be handled in back-end
+       -->
+      <!-- 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" packable="false">
+        <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="40" equivalent="full"/>
+      <input name="cin" num_pins="1"/>
+      <input name="regin" num_pins="1"/>
+      <input name="scin" num_pins="1"/>
+      <output name="O" num_pins="20" equivalent="none"/>
+      <output name="cout" num_pins="1"/>
+      <output name="regout" num_pins="1"/>
+      <output name="scout" num_pins="1"/>
+      <clock name="clk" num_pins="1"/>
+      <!-- Describe fracturable logic element.  
+             Each fracturable logic element has a 6-LUT that can alternatively operate as two 5-LUTs with shared inputs. 
+             The outputs of the fracturable logic element can be optionally registered
+        -->
+      <pb_type name="fle" num_pb="10">
+        <input name="in" num_pins="6"/>
+        <input name="cin" num_pins="1"/>
+        <input name="regin" num_pins="1"/>
+        <input name="scin" num_pins="1"/>
+        <output name="out" num_pins="2"/>
+        <output name="cout" num_pins="1"/>
+        <output name="regout" num_pins="1"/>
+        <output name="scout" num_pins="1"/>
+        <clock name="clk" num_pins="1"/>
+        <!-- Physical mode definition begin (physical implementation of the fle) -->
+        <mode name="physical" packable="false">
+          <pb_type name="fabric" num_pb="1">
+            <input name="in" num_pins="6"/>
+            <input name="cin" num_pins="1"/>
+            <input name="regin" num_pins="1"/>
+            <input name="scin" num_pins="1"/>
+            <output name="out" num_pins="2"/>
+            <output name="cout" num_pins="1"/>
+            <output name="regout" num_pins="1"/>
+            <output name="scout" num_pins="1"/>
+            <clock name="clk" num_pins="1"/>
+            <pb_type name="frac_logic" num_pb="1">
+              <input name="in" num_pins="6"/>
+              <output name="lut4_out" num_pins="4"/>
+              <output name="out" num_pins="2"/>
+              <!-- Define LUT -->
+              <pb_type name="frac_lut6" blif_model=".subckt frac_lut6" num_pb="1">
+                <input name="in" num_pins="6"/>
+                <output name="lut4_out" num_pins="4"/>
+                <output name="lut5_out" num_pins="2"/>
+                <output name="lut6_out" num_pins="1"/>
+              </pb_type>
+              <interconnect>
+                <direct name="direct1" input="frac_logic.in" output="frac_lut6.in"/>
+                <direct name="direct2" input="frac_lut6.lut4_out" output="frac_logic.lut4_out"/>
+                <direct name="direct3" input="frac_lut6.lut5_out[1]" output="frac_logic.out[1]"/>
+                <!-- Xifan Tang: I use out[0] because the output of lut6 in lut6 mode is wired to the out[0] -->
+                <mux name="mux1" input="frac_lut6.lut6_out frac_lut6.lut5_out[0]" output="frac_logic.out[0]"/>
+              </interconnect>
+            </pb_type>
+            <!-- Define flip-flop with scan-chain capability, DI is the scan-chain data input -->
+            <pb_type name="ff" blif_model=".subckt scff" num_pb="2">
+              <input name="D" num_pins="1"/>
+              <input name="DI" num_pins="1"/>
+              <output name="Q" num_pins="1"/>
+              <clock name="clk" num_pins="1"/>
+              <T_setup value="66e-12" port="ff.D" clock="clk"/>
+              <T_setup value="66e-12" port="ff.DI" clock="clk"/>
+              <T_clock_to_Q max="124e-12" port="ff.Q" clock="clk"/>
+            </pb_type>         
+            <!-- Define adders -->
+            <pb_type name="adder" blif_model=".subckt adder" num_pb="2">
+              <input name="a" num_pins="1"/>
+              <input name="b" num_pins="1"/>
+              <input name="cin" num_pins="1"/>
+              <output name="cout" num_pins="1"/>
+              <output name="sumout" num_pins="1"/>
+              <delay_constant max="0.3e-9" in_port="adder.a" out_port="adder.sumout"/>
+              <delay_constant max="0.3e-9" in_port="adder.b" out_port="adder.sumout"/>
+              <delay_constant max="0.3e-9" in_port="adder.cin" out_port="adder.sumout"/>
+              <delay_constant max="0.3e-9" in_port="adder.a" out_port="adder.cout"/>
+              <delay_constant max="0.3e-9" in_port="adder.b" out_port="adder.cout"/>
+              <delay_constant max="0.01e-9" in_port="adder.cin" out_port="adder.cout"/>
+            </pb_type>
+            <interconnect>
+              <direct name="direct1" input="fabric.in" output="frac_logic.in"/>
+              <direct name="direct2" input="fabric.cin" output="adder[0:0].cin"/>
+              <direct name="direct3" input="adder[0:0].cout" output="adder[1:1].cin"/>
+              <direct name="direct4" input="adder[1:1].cout" output="fabric.cout"/>
+              <direct name="direct5" input="frac_logic.lut4_out[0:0]" output="adder[0:0].a"/>
+              <direct name="direct6" input="frac_logic.lut4_out[1:1]" output="adder[0:0].b"/>
+              <direct name="direct7" input="frac_logic.lut4_out[2:2]" output="adder[1:1].a"/>
+              <direct name="direct8" input="frac_logic.lut4_out[3:3]" output="adder[1:1].b"/>
+              <direct name="direct9" input="fabric.scin" output="ff[0].DI"/>
+              <direct name="direct10" input="ff[0].Q" output="ff[1].DI"/>
+              <direct name="direct11" input="ff[1].Q" output="fabric.scout"/>
+              <complete name="complete1" input="fabric.clk" output="ff[1:0].clk"/>
+              <mux name="mux1" input="adder[0].sumout frac_logic.out[0] fabric.regin" output="ff[0].D">
+                <delay_constant max="25e-12" in_port="adder[0].sumout frac_logic.out[0] fabric.regin" out_port="ff[0].D"/>
+              </mux>
+              <mux name="mux2" input="adder[1].sumout frac_logic.out[1] ff[0].Q" output="ff[1].D">
+                <delay_constant max="25e-12" in_port="adder[1].sumout frac_logic.out[1] ff[0].Q" out_port="ff[1].D"/>
+              </mux>
+              <mux name="mux3" input="adder[0].sumout ff[0].Q frac_logic.out[0]" output="fabric.out[0]">
+                <!-- LUT to output is faster than FF to output on a Stratix IV -->
+                <delay_constant max="25e-12" in_port="frac_logic.out[0]" out_port="fabric.out[0]"/>
+                <delay_constant max="45e-12" in_port="ff[0].Q" out_port="fabric.out[0]"/>
+              </mux>
+              <mux name="mux4" input="adder[1].sumout ff[1].Q frac_logic.out[1]" output="fabric.out[1]">
+                <!-- LUT to output is faster than FF to output on a Stratix IV -->
+                <delay_constant max="25e-12" in_port="frac_logic.out[1]" out_port="fabric.out[1]"/>
+                <delay_constant max="45e-12" in_port="ff[1].Q" out_port="fabric.out[1]"/>
+              </mux>
+            </interconnect>
+          </pb_type>
+          <interconnect>
+            <direct name="direct1" input="fle.in" output="fabric.in"/>
+            <direct name="direct2" input="fle.cin" output="fabric.cin"/>
+            <direct name="direct3" input="fle.regin" output="fabric.regin"/>
+            <direct name="direct4" input="fle.scin" output="fabric.scin"/>
+            <direct name="direct5" input="fabric.out" output="fle.out"/>
+            <direct name="direct6" input="fabric.cout" output="fle.cout"/>
+            <direct name="direct7" input="fabric.regout" output="fle.regout"/>
+            <direct name="direct8" input="fabric.scout" output="fle.scout"/>
+            <direct name="direct9" input="fle.clk" output="fabric.clk"/>
+          </interconnect>
+        </mode>
+        <!-- Physical mode definition end (physical implementation of the fle) -->
+        <!-- BEGIN fle mode of dual lut5 -->
+        <mode name="n2_lut5">
+          <pb_type name="ble5" num_pb="2">
+            <input name="in" num_pins="5"/>
+            <output name="out" num_pins="1"/>
+            <clock name="clk" num_pins="1"/>
+            <!-- Regular LUT mode -->
+            <pb_type name="lut5" blif_model=".names" num_pb="1" class="lut">
+              <input name="in" num_pins="5" port_class="lut_in"/>
+              <output name="out" num_pins="1" port_class="lut_out"/>
+              <!-- LUT timing using delay matrix -->
+              <!-- These are the physical delay inputs on a Stratix IV LUT but because VPR cannot do LUT rebalancing,
+                  we instead take the average of these numbers to get more stable results
+                82e-12
+                173e-12
+                261e-12
+                263e-12
+                398e-12
+                -->
+              <delay_matrix type="max" in_port="lut5.in" out_port="lut5.out">
+                235e-12
+                235e-12
+                235e-12
+                235e-12
+                235e-12
+              </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="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="ble5.in" output="lut5.in"/>
+              <direct name="direct2" input="lut5.out" output="ff.D">
+                <pack_pattern name="ble5" in_port="lut5.out" out_port="ff.D"/>
+              </direct>
+              <direct name="direct3" input="ble5.clk" output="ff.clk"/>
+              <mux name="mux1" input="ff.Q lut5.out" output="ble5.out">
+                <delay_constant max="25e-12" in_port="lut5.out" out_port="ble5.out"/>
+                <delay_constant max="45e-12" in_port="ff.Q" out_port="ble5.out"/>
+              </mux>
+            </interconnect>
+          </pb_type>
+          <interconnect>
+            <direct name="direct1" input="fle.in[4:0]" output="ble5[0:0].in"/>
+            <direct name="direct2" input="fle.in[4:0]" output="ble5[1:1].in"/>
+            <complete name="direct3" input="fle.clk" output="ble5.clk"/>
+            <direct name="direct4" input="ble5.out" output="fle.out"/>
+          </interconnect>
+        </mode>
+        <!-- END fle mode of dual lut5 -->
+        <!-- BEGIN arithmetic mode of dual lut4 + adders -->
+        <mode name="arithmetic">
+          <pb_type name="arithmetic" num_pb="2">
+            <input name="in" num_pins="4"/>
+            <input name="cin" num_pins="1"/>
+            <output name="out" num_pins="1"/>
+            <output name="cout" num_pins="1"/>
+            <clock name="clk" num_pins="1"/>
+            <!-- Special dual-LUT mode that drives adder only -->
+            <pb_type name="lut4" blif_model=".names" num_pb="2" 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 -->
+              <!-- These are the physical delay inputs on a Stratix IV LUT but because VPR cannot do LUT rebalancing,
+                       we instead take the average of these numbers to get more stable results
+                  82e-12
+                  173e-12
+                  261e-12
+                  263e-12
+                  -->
+              <delay_matrix type="max" in_port="lut4.in" out_port="lut4.out">
+                  195e-12
+                  195e-12
+                  195e-12
+                  195e-12
+                </delay_matrix>
+            </pb_type>
+            <pb_type name="adder" blif_model=".subckt adder" num_pb="1">
+              <input name="a" num_pins="1"/>
+              <input name="b" num_pins="1"/>
+              <input name="cin" num_pins="1"/>
+              <output name="cout" num_pins="1"/>
+              <output name="sumout" num_pins="1"/>
+              <delay_constant max="0.3e-9" in_port="adder.a" out_port="adder.sumout"/>
+              <delay_constant max="0.3e-9" in_port="adder.b" out_port="adder.sumout"/>
+              <delay_constant max="0.3e-9" in_port="adder.cin" out_port="adder.sumout"/>
+              <delay_constant max="0.3e-9" in_port="adder.a" out_port="adder.cout"/>
+              <delay_constant max="0.3e-9" in_port="adder.b" out_port="adder.cout"/>
+              <delay_constant max="0.01e-9" in_port="adder.cin" out_port="adder.cout"/>
+            </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="66e-12" port="ff.D" clock="clk"/>
+              <T_clock_to_Q max="124e-12" port="ff.Q" clock="clk"/>
+            </pb_type>
+            <interconnect>
+              <direct name="clock" input="arithmetic.clk" output="ff.clk"/>
+              <direct name="lut_in1" input="arithmetic.in[3:0]" output="lut4[0:0].in[3:0]"/>
+              <direct name="lut_in2" input="arithmetic.in[3:0]" output="lut4[1:1].in[3:0]"/>
+              <direct name="lut_to_add1" input="lut4[0:0].out" output="adder.a">
+                </direct>
+              <direct name="lut_to_add2" input="lut4[1:1].out" output="adder.b">
+                </direct>
+              <direct name="add_to_ff" input="adder.sumout" output="ff.D">
+                <pack_pattern name="chain" in_port="adder.sumout" out_port="ff.D"/>
+              </direct>
+              <direct name="carry_in" input="arithmetic.cin" output="adder.cin">
+                <pack_pattern name="chain" in_port="arithmetic.cin" out_port="adder.cin"/>
+              </direct>
+              <direct name="carry_out" input="adder.cout" output="arithmetic.cout">
+                <pack_pattern name="chain" in_port="adder.cout" out_port="arithmetic.cout"/>
+              </direct>
+              <mux name="sumout" input="ff.Q adder.sumout" output="arithmetic.out">
+                <delay_constant max="25e-12" in_port="adder.sumout" out_port="arithmetic.out"/>
+                <delay_constant max="45e-12" in_port="ff.Q" out_port="arithmetic.out"/>
+              </mux>
+            </interconnect>
+          </pb_type>
+          <interconnect>
+            <direct name="direct1" input="fle.in[3:0]" output="arithmetic[0:0].in"/>
+            <direct name="direct2" input="fle.in[3:0]" output="arithmetic[1:1].in"/>
+            <direct name="carry_in" input="fle.cin" output="arithmetic[0:0].cin">
+              <pack_pattern name="chain" in_port="fle.cin" out_port="arithmetic[0:0].cin"/>
+            </direct>
+            <direct name="carry_inter" input="arithmetic[0:0].cout" output="arithmetic[1:1].cin">
+              <pack_pattern name="chain" in_port="arithmetic[0:0].cout" out_port="arithmetic[1:1].cin"/>
+            </direct>
+            <direct name="carry_out" input="arithmetic[1:1].cout" output="fle.cout">
+              <pack_pattern name="chain" in_port="arithmetic.cout" out_port="fle.cout"/>
+            </direct>
+            <complete name="direct3" input="fle.clk" output="arithmetic.clk"/>
+            <direct name="direct4" input="arithmetic.out" output="fle.out"/>
+          </interconnect>
+        </mode>
+        <!-- n2_lut5 -->
+        <mode name="n1_lut6">
+          <pb_type name="ble6" num_pb="1">
+            <input name="in" num_pins="6"/>
+            <output name="out" num_pins="1"/>
+            <clock name="clk" num_pins="1"/>
+            <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 -->
+              <!-- These are the physical delay inputs on a Stratix IV LUT but because VPR cannot do LUT rebalancing,
+                       we instead take the average of these numbers to get more stable results
+                  82e-12
+                  173e-12
+                  261e-12
+                  263e-12
+                  398e-12
+                  397e-12
+                  -->
+              <delay_matrix type="max" in_port="lut6.in" out_port="lut6.out">
+                  261e-12
+                  261e-12
+                  261e-12
+                  261e-12
+                  261e-12
+                  261e-12
+                </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="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">
+                <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">
+                <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[5:0]" 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>
+        <!-- Define n1_lut6 end -->
+        <!-- Define shift register begin -->
+        <mode name="shift_register">
+          <pb_type name="shift_reg" num_pb="1">
+            <input name="regin" num_pins="1"/>
+            <output name="regout" num_pins="1"/>
+            <clock name="clk" num_pins="1"/>
+            <pb_type name="ff" blif_model=".latch" num_pb="2" 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="shift_reg.regin" output="ff[0].D"/>
+              <direct name="direct2" input="ff[0].Q" output="ff[1].D"/>
+              <direct name="direct3" input="ff[1].Q" output="shift_reg.regout"/>
+              <complete name="complete1" input="shift_reg.clk" output="ff.clk"/>
+            </interconnect>
+          </pb_type>
+          <interconnect>
+            <direct name="direct1" input="fle.regin" output="shift_reg.regin"/>
+            <direct name="direct2" input="shift_reg.regout" output="fle.regout"/>
+            <direct name="direct3" input="fle.clk" output="shift_reg.clk"/>
+          </interconnect>
+        </mode>
+        <!-- Define shift register end --> 
+      </pb_type>
+      <interconnect>
+        <!-- We use a 50% depop crossbar built using small full xbars to get sets of logically equivalent pins 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[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[0:0]" output="clb.O[9:0]"/>
+        <direct name="clbouts2" input="fle[9:0].out[1:1]" output="clb.O[19:10]"/>
+        <!-- Carry chain links -->
+        <direct name="carry_in" input="clb.cin" output="fle[0:0].cin">
+          <!-- Put all inter-block carry chain delay on this one edge -->
+          <delay_constant max="0.16e-9" in_port="clb.cin" out_port="fle[0:0].cin"/>
+          <pack_pattern name="chain" in_port="clb.cin" out_port="fle[0:0].cin"/>
+        </direct>
+        <direct name="carry_out" input="fle[9:9].cout" output="clb.cout">
+          <pack_pattern name="chain" in_port="fle[9:9].cout" out_port="clb.cout"/>
+        </direct>
+        <direct name="carry_link" input="fle[8:0].cout" output="fle[9:1].cin">
+          <pack_pattern name="chain" in_port="fle[8:0].cout" out_port="fle[9:1].cin"/>
+        </direct>
+        <!-- Shift register chain links -->
+        <direct name="shift_register_in" input="clb.regin" output="fle[0:0].regin">
+          <!-- Put all inter-block carry chain delay on this one edge -->
+          <delay_constant max="0.16e-9" in_port="clb.regin" out_port="fle[0:0].regin"/>
+          <pack_pattern name="chain" in_port="clb.regin" out_port="fle[0:0].regin"/>
+        </direct>
+        <direct name="shift_register_out" input="fle[9:9].regout" output="clb.regout">
+          <pack_pattern name="chain" in_port="fle[9:9].regout" out_port="clb.regout"/>
+        </direct>
+        <direct name="shift_register_link" input="fle[8:0].regout" output="fle[9:1].regin">
+          <pack_pattern name="chain" in_port="fle[8:0].regout" out_port="fle[9:1].regin"/>
+        </direct>
+        <!-- Scan chain links -->
+        <direct name="scan_chain_in" input="clb.scin" output="fle[0:0].scin">
+          <!-- Put all inter-block carry chain delay on this one edge -->
+          <delay_constant max="0.16e-9" in_port="clb.scin" out_port="fle[0:0].scin"/>
+        </direct>
+        <direct name="scan_chain_out" input="fle[9:9].scout" output="clb.scout">
+        </direct>
+        <direct name="scan_chain_link" input="fle[8:0].scout" output="fle[9:1].scin">
+        </direct>
+      </interconnect>
+    </pb_type>
+    <!-- Define general purpose logic block (CLB) ends -->
+  </complexblocklist>
+</architecture>

openfpga_flow/openfpga_arch/k6_frac_N10_adder_chain_mem16K_40nm_openfpga.xml

@@ -189,7 +189,7 @@
       <port type="output" prefix="sumout" size="1"/>
       <port type="output" prefix="cout" size="1"/>
     </circuit_model>
-    <circuit_model type="hard_logic" name="dpram_512x32" prefix="dpram_512x32" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/SpiceNetlists/dpram.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/VerilogNetlists/dpsram.v">
+    <circuit_model type="hard_logic" name="dpram_512x32" prefix="dpram_512x32" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/SpiceNetlists/dpram.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/VerilogNetlists/dpram16k.v">
       <design_technology type="cmos"/>
       <input_buffer exist="true" circuit_model_name="INVTX1"/>
       <output_buffer exist="true" circuit_model_name="INVTX1"/>

openfpga_flow/openfpga_arch/k6_frac_N10_adder_chain_mem16K_aib_40nm_openfpga.xml

@@ -189,7 +189,7 @@
       <port type="output" prefix="sumout" size="1"/>
       <port type="output" prefix="cout" size="1"/>
     </circuit_model>
-    <circuit_model type="hard_logic" name="dpram_512x32" prefix="dpram_512x32" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/SpiceNetlists/dpram.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/VerilogNetlists/dpsram.v">
+    <circuit_model type="hard_logic" name="dpram_512x32" prefix="dpram_512x32" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/SpiceNetlists/dpram.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/VerilogNetlists/dpram16k.v">
       <design_technology type="cmos"/>
       <input_buffer exist="true" circuit_model_name="INVTX1"/>
       <output_buffer exist="true" circuit_model_name="INVTX1"/>

openfpga_flow/openfpga_arch/k6_frac_N10_adder_register_scan_chain_40nm_openfpga.xml

@@ -137,7 +137,7 @@
         This is flip-flop with scan-chain feature.
         When the TESTEN is enabled, the data will be propagated form DI instead of D
       -->
-    <circuit_model type="ff" name="static_dff" prefix="dff" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/SpiceNetlists/ff.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/VerilogNetlists/ff.v">
+    <circuit_model type="ff" name="scan_chain_ff" prefix="scan_chain_ff" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/SpiceNetlists/ff.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/VerilogNetlists/ff.v">
        <design_technology type="cmos"/>
        <input_buffer exist="true" circuit_model_name="INVTX1"/>
        <output_buffer exist="true" circuit_model_name="INVTX1"/>
@@ -228,7 +228,7 @@
     </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="static_dff"/>
+    <pb_type name="clb.fle[physical].fabric.ff" circuit_model_name="scan_chain_ff"/>
     <pb_type name="clb.fle[physical].fabric.adder" circuit_model_name="adder"/>
     <!-- Binding operating pb_type to physical pb_type -->
     <!-- Binding operating pb_types in mode 'n2_lut5' -->

openfpga_flow/openfpga_arch/k6_frac_N10_behavioral_40nm_openfpga.xml

@@ -0,0 +1,260 @@
+<!-- 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"/>
+      <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"/>
+      <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"/>
+      <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"/>
+      <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"/>
+      <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">
+      <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">
+      <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">
+      <design_technology type="cmos" structure="one_level" add_const_input="true" const_input_val="1"/>
+      <input_buffer exist="true" circuit_model_name="INVTX1"/>
+      <output_buffer exist="true" circuit_model_name="tap_buf4"/>
+      <pass_gate_logic circuit_model_name="TGATE"/>
+      <port type="input" prefix="in" size="1"/>
+      <port type="output" prefix="out" size="1"/>
+      <port type="sram" prefix="sram" size="1"/>
+    </circuit_model>
+    <!--DFF subckt ports should be defined as <D> <Q> <CLK> <RESET> <SET>  -->
+    <circuit_model type="ff" name="static_dff" prefix="dff" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/SpiceNetlists/ff.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/VerilogNetlists/ff.v">
+       <design_technology type="cmos"/>
+       <input_buffer exist="true" circuit_model_name="INVTX1"/>
+       <output_buffer exist="true" circuit_model_name="INVTX1"/>
+       <port type="input" prefix="D" size="1"/>
+       <port type="input" prefix="set" size="1" is_global="true" default_val="0" is_set="true"/>
+       <port type="input" prefix="reset" size="1" is_global="true" default_val="0" is_reset="true"/>
+       <port type="output" prefix="Q" size="1"/>
+       <port type="clock" prefix="clk" size="1" is_global="true" default_val="0" />
+    </circuit_model>
+    <circuit_model type="lut" name="frac_lut6" prefix="frac_lut6">
+      <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="-----1" circuit_model_name="OR2"/>
+      <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="1" mode_select="true" circuit_model_name="sc_dff_compact" 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="sc_dff_compact" prefix="scff" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/SpiceNetlists/ff.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/VerilogNetlists/ff.v">
+       <design_technology type="cmos"/>
+       <input_buffer exist="true" circuit_model_name="INVTX1"/>
+       <output_buffer exist="true" circuit_model_name="INVTX1"/>
+       <port type="input" prefix="pReset" lib_name="reset" 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="Qb" size="1"/>
+       <port type="clock" prefix="prog_clk" lib_name="clk" size="1" is_global="true" default_val="0" is_prog="true"/>
+    </circuit_model>
+    <circuit_model type="iopad" name="iopad" prefix="iopad" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/SpiceNetlists/io.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/VerilogNetlists/io.v">
+      <design_technology type="cmos"/>
+      <input_buffer exist="true" circuit_model_name="INVTX1"/>
+      <output_buffer exist="true" circuit_model_name="INVTX1"/>
+      <port type="inout" prefix="pad" size="1" is_global="true" is_io="true"/>
+      <port type="sram" prefix="en" size="1" mode_select="true" circuit_model_name="sc_dff_compact" default_val="1"/>
+      <port type="input" prefix="outpad" size="1"/>
+      <port type="output" prefix="inpad" size="1"/>
+    </circuit_model>
+  </circuit_library>
+  <configuration_protocol>
+    <organization type="scan_chain" circuit_model_name="sc_dff_compact"/>
+  </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>
+  <pb_type_annotations>
+    <!-- physical pb_type binding in complex block IO -->
+    <pb_type name="io" physical_mode_name="physical" idle_mode_name="inpad"/>
+    <pb_type name="io[physical].iopad" circuit_model_name="iopad" mode_bits="1"/> 
+    <pb_type name="io[inpad].inpad" physical_pb_type_name="io[physical].iopad" mode_bits="1"/> 
+    <pb_type name="io[outpad].outpad" physical_pb_type_name="io[physical].iopad" mode_bits="0"/> 
+    <!-- End physical pb_type binding in complex block IO -->
+
+    <!-- physical pb_type binding in complex block CLB -->
+    <!-- physical mode will be the default mode if not specified -->
+    <pb_type name="clb">
+      <!-- Binding interconnect to circuit models as their physical implementation, if not defined, we use the default model -->
+      <interconnect name="crossbar" circuit_model_name="mux_2level"/>
+    </pb_type>
+    <pb_type name="clb.fle" physical_mode_name="physical"/>
+    <pb_type name="clb.fle[physical].fabric.frac_logic.frac_lut6" circuit_model_name="frac_lut6" mode_bits="0"/>
+    <pb_type name="clb.fle[physical].fabric.ff" circuit_model_name="static_dff"/>
+    <!-- Binding operating pb_type to physical pb_type -->
+    <pb_type name="clb.fle[n2_lut5].lut5inter.ble5.lut5" physical_pb_type_name="clb.fle[physical].fabric.frac_logic.frac_lut6" mode_bits="1" 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].lut5inter.ble5.ff" physical_pb_type_name="clb.fle[physical].fabric.ff"/>
+    <pb_type name="clb.fle[n1_lut6].ble6.lut6" physical_pb_type_name="clb.fle[physical].fabric.frac_logic.frac_lut6" mode_bits="0">
+      <!-- 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 IO -->
+  </pb_type_annotations>
+</openfpga_architecture>
+<openfpga_simulation_setting>
+  <clock_setting>
+    <!--operating frequency="auto" num_cycles="auto" slack="0.2"/-->
+    <operating frequency="200e6" num_cycles="auto" slack="0.2"/>
+    <programming frequency="10e6"/>
+  </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>

openfpga_flow/openfpga_arch/k6_frac_N10_stdcell_mux_40nm_openfpga.xml

@@ -82,13 +82,13 @@
          If your standard cell provider does not offer the exact truth table,
          you can simply swap the inputs as shown in the example below
       -->
-    <circuit_model type="gate" name="stdcell_mux2" prefix="stdcell_mux2" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/SpiceNetlists/sc_mux2.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/VerilogNetlists/sc_mux2.v">
+    <circuit_model type="gate" name="MUX2" prefix="MUX2" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/SpiceNetlists/mux2.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/VerilogNetlists/mux2.v">
       <design_technology type="cmos" topology="MUX2"/>
       <input_buffer exist="false"/>
       <output_buffer exist="false"/>
       <port type="input" prefix="in0" lib_name="B" size="1"/>
       <port type="input" prefix="in1" lib_name="A" size="1"/>
-      <port type="input" prefix="sel" lib_name="S" size="1"/>
+      <port type="input" prefix="sel" lib_name="S0" size="1"/>
       <port type="output" prefix="out" lib_name="Y" size="1"/>
     </circuit_model>
     <circuit_model type="chan_wire" name="chan_segment" prefix="track_seg" is_default="true">
@@ -111,7 +111,7 @@
       <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="stdcell_mux2"/>
+      <pass_gate_logic circuit_model_name="MUX2"/>
       <port type="input" prefix="in" size="1"/>
       <port type="output" prefix="out" size="1"/>
       <port type="sram" prefix="sram" size="1"/>
@@ -120,7 +120,7 @@
       <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="stdcell_mux2"/>
+      <pass_gate_logic circuit_model_name="MUX2"/>
       <port type="input" prefix="in" size="1"/>
       <port type="output" prefix="out" size="1"/>
       <port type="sram" prefix="sram" size="1"/>
@@ -143,7 +143,7 @@
       <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="stdcell_mux2"/>
+      <pass_gate_logic circuit_model_name="MUX2"/>
       <port type="input" prefix="in" size="6" tri_state_map="-----1" circuit_model_name="OR2"/>
       <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"/>

openfpga_flow/tasks/openfpga_shell/behavioral_verilog/config/task.conf

@@ -0,0 +1,34 @@
+# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
+# 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
+openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/example_script.openfpga
+power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
+power_analysis = true
+spice_output=false
+verilog_output=true
+timeout_each_job = 20*60
+fpga_flow=vpr_blif
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k6_frac_N10_behavioral_40nm_openfpga.xml
+
+[ARCHITECTURES]
+arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_40nm.xml
+
+[BENCHMARKS]
+bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.blif
+
+[SYNTHESIS_PARAM]
+bench0_top = top
+bench0_act = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.act
+bench0_verilog = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.v
+bench0_chan_width = 300
+
+[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
+end_flow_with_test=
+vpr_fpga_verilog_formal_verification_top_netlist=

openfpga_flow/tasks/openfpga_shell/bram/dpram16k/config/task.conf

@@ -0,0 +1,34 @@
+# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
+# 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
+openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/example_script.openfpga
+power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
+power_analysis = true
+spice_output=false
+verilog_output=true
+timeout_each_job = 20*60
+fpga_flow=vpr_blif
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k6_frac_N10_adder_chain_mem16K_40nm_openfpga.xml
+
+[ARCHITECTURES]
+arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_adder_chain_mem16K_40nm.xml
+
+[BENCHMARKS]
+bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.blif
+
+[SYNTHESIS_PARAM]
+bench0_top = top
+bench0_act = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.act
+bench0_verilog = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.v
+bench0_chan_width = 300
+
+[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
+end_flow_with_test=
+vpr_fpga_verilog_formal_verification_top_netlist=

openfpga_flow/tasks/openfpga_shell/bram/wide_dpram16k/config/task.conf

@@ -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
+openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/example_script.openfpga
+power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
+power_analysis = true
+spice_output=false
+verilog_output=true
+timeout_each_job = 20*60
+fpga_flow=vpr_blif
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k6_frac_N10_adder_chain_mem16K_40nm_openfpga.xml
+
+
+[ARCHITECTURES]
+arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_adder_chain_wide_mem16K_40nm.xml
+
+[BENCHMARKS]
+bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.blif
+
+[SYNTHESIS_PARAM]
+bench0_top = top
+bench0_act = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.act
+bench0_verilog = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.v
+bench0_chan_width = 300
+
+[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
+end_flow_with_test=
+vpr_fpga_verilog_formal_verification_top_netlist=

openfpga_flow/tasks/openfpga_shell/duplicated_grid_pin/config/task.conf

@@ -0,0 +1,34 @@
+# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
+# 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
+openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/duplicated_grid_pin_example_script.openfpga
+power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
+power_analysis = true
+spice_output=false
+verilog_output=true
+timeout_each_job = 20*60
+fpga_flow=vpr_blif
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k6_frac_N10_40nm_openfpga.xml
+
+[ARCHITECTURES]
+arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_40nm.xml
+
+[BENCHMARKS]
+bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.blif
+
+[SYNTHESIS_PARAM]
+bench0_top = top
+bench0_act = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.act
+bench0_verilog = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.v
+bench0_chan_width = 300
+
+[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
+end_flow_with_test=
+vpr_fpga_verilog_formal_verification_top_netlist=

openfpga_flow/tasks/openfpga_shell/fabric_chain/adder_chain/config/task.conf

@@ -0,0 +1,34 @@
+# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
+# 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
+openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/example_script.openfpga
+power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
+power_analysis = true
+spice_output=false
+verilog_output=true
+timeout_each_job = 20*60
+fpga_flow=vpr_blif
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k6_frac_N10_adder_column_chain_40nm_openfpga.xml
+
+[ARCHITECTURES]
+arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_adder_chain_40nm.xml
+
+[BENCHMARKS]
+bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.blif
+
+[SYNTHESIS_PARAM]
+bench0_top = top
+bench0_act = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.act
+bench0_verilog = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.v
+bench0_chan_width = 300
+
+[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
+end_flow_with_test=
+vpr_fpga_verilog_formal_verification_top_netlist=

openfpga_flow/tasks/openfpga_shell/fabric_chain/register_chain/config/task.conf

@@ -0,0 +1,34 @@
+# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
+# 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
+openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/example_script.openfpga
+power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
+power_analysis = true
+spice_output=false
+verilog_output=true
+timeout_each_job = 20*60
+fpga_flow=vpr_blif
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k6_frac_N10_adder_register_chain_40nm_openfpga.xml
+
+[ARCHITECTURES]
+arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_adder_register_chain_40nm.xml
+
+[BENCHMARKS]
+bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.blif
+
+[SYNTHESIS_PARAM]
+bench0_top = top
+bench0_act = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.act
+bench0_verilog = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.v
+bench0_chan_width = 300
+
+[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
+end_flow_with_test=
+vpr_fpga_verilog_formal_verification_top_netlist=

openfpga_flow/tasks/openfpga_shell/fabric_chain/scan_chain/config/task.conf

@@ -0,0 +1,34 @@
+# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
+# 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
+openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/example_script.openfpga
+power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
+power_analysis = true
+spice_output=false
+verilog_output=true
+timeout_each_job = 20*60
+fpga_flow=vpr_blif
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k6_frac_N10_adder_register_scan_chain_40nm_openfpga.xml
+
+[ARCHITECTURES]
+arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_adder_register_scan_chain_40nm.xml
+
+[BENCHMARKS]
+bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.blif
+
+[SYNTHESIS_PARAM]
+bench0_top = top
+bench0_act = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.act
+bench0_verilog = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.v
+bench0_chan_width = 300
+
+[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
+end_flow_with_test=
+vpr_fpga_verilog_formal_verification_top_netlist=

openfpga_flow/tasks/openfpga_shell/flatten_routing/config/task.conf

@@ -0,0 +1,34 @@
+# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
+# 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
+openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/flatten_routing_example_script.openfpga
+power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
+power_analysis = true
+spice_output=false
+verilog_output=true
+timeout_each_job = 20*60
+fpga_flow=vpr_blif
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k6_frac_N10_40nm_openfpga.xml
+
+[ARCHITECTURES]
+arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_40nm.xml
+
+[BENCHMARKS]
+bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.blif
+
+[SYNTHESIS_PARAM]
+bench0_top = top
+bench0_act = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.act
+bench0_verilog = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.v
+bench0_chan_width = 300
+
+[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
+end_flow_with_test=
+vpr_fpga_verilog_formal_verification_top_netlist=

openfpga_flow/tasks/openfpga_shell/frac_lut/config/task.conf

@@ -0,0 +1,34 @@
+# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
+# 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
+openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/example_script.openfpga
+power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
+power_analysis = true
+spice_output=false
+verilog_output=true
+timeout_each_job = 20*60
+fpga_flow=vpr_blif
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k6_frac_N10_40nm_openfpga.xml
+
+[ARCHITECTURES]
+arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_40nm.xml
+
+[BENCHMARKS]
+bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.blif
+
+[SYNTHESIS_PARAM]
+bench0_top = top
+bench0_act = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.act
+bench0_verilog = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.v
+bench0_chan_width = 300
+
+[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
+end_flow_with_test=
+vpr_fpga_verilog_formal_verification_top_netlist=

openfpga_flow/tasks/openfpga_shell/hard_adder/config/task.conf

@@ -0,0 +1,34 @@
+# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
+# 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
+openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/example_script.openfpga
+power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
+power_analysis = true
+spice_output=false
+verilog_output=true
+timeout_each_job = 20*60
+fpga_flow=vpr_blif
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k6_frac_N10_adder_chain_40nm_openfpga.xml
+
+[ARCHITECTURES]
+arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_adder_chain_40nm.xml
+
+[BENCHMARKS]
+bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.blif
+
+[SYNTHESIS_PARAM]
+bench0_top = top
+bench0_act = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.act
+bench0_verilog = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.v
+bench0_chan_width = 300
+
+[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
+end_flow_with_test=
+vpr_fpga_verilog_formal_verification_top_netlist=

openfpga_flow/tasks/openfpga_shell/implicit_verilog/config/task.conf

@@ -0,0 +1,34 @@
+# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
+# 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
+openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/implicit_verilog_example_script.openfpga
+power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
+power_analysis = true
+spice_output=false
+verilog_output=true
+timeout_each_job = 20*60
+fpga_flow=vpr_blif
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k6_frac_N10_40nm_openfpga.xml
+
+[ARCHITECTURES]
+arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_40nm.xml
+
+[BENCHMARKS]
+bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.blif
+
+[SYNTHESIS_PARAM]
+bench0_top = top
+bench0_act = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.act
+bench0_verilog = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.v
+bench0_chan_width = 300
+
+[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
+end_flow_with_test=
+vpr_fpga_verilog_formal_verification_top_netlist=

openfpga_flow/tasks/openfpga_shell/io/aib/config/task.conf

@@ -0,0 +1,45 @@
+# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
+# 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
+openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/example_script.openfpga
+power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
+power_analysis = true
+spice_output=false
+verilog_output=true
+timeout_each_job = 20*60
+fpga_flow=vpr_blif
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k6_frac_N10_adder_chain_mem16K_aib_40nm_openfpga.xml
+
+#####################################
+# Debugging status 
+# Fail in the following cases
+# - tileable routing is used
+# - vpr routing is used
+# - compressed routing is enabled/disabled
+# - duplicated pin is enabled/disabled
+#
+# Therefore, this could be a bug in the VPR
+####################################
+
+[ARCHITECTURES]
+arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_adder_chain_mem16K_aib_40nm.xml
+
+[BENCHMARKS]
+bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.blif
+
+[SYNTHESIS_PARAM]
+bench0_top = top
+bench0_act = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.act
+bench0_verilog = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.v
+bench0_chan_width = 300
+
+[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
+end_flow_with_test=
+vpr_fpga_verilog_formal_verification_top_netlist=

openfpga_flow/tasks/openfpga_shell/io/multi_io_capacity/config/task.conf

@@ -0,0 +1,34 @@
+# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
+# 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
+openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/example_script.openfpga
+power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
+power_analysis = true
+spice_output=false
+verilog_output=true
+timeout_each_job = 20*60
+fpga_flow=vpr_blif
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k6_frac_N10_adder_chain_mem16K_40nm_openfpga.xml
+
+[ARCHITECTURES]
+arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_adder_chain_mem16K_multi_io_capacity_40nm.xml
+
+[BENCHMARKS]
+bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.blif
+
+[SYNTHESIS_PARAM]
+bench0_top = top
+bench0_act = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.act
+bench0_verilog = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.v
+bench0_chan_width = 300
+
+[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
+end_flow_with_test=
+vpr_fpga_verilog_formal_verification_top_netlist=

openfpga_flow/tasks/openfpga_shell/io/reduced_io/config/task.conf

@@ -0,0 +1,34 @@
+# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
+# 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
+openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/example_script.openfpga
+power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
+power_analysis = true
+spice_output=false
+verilog_output=true
+timeout_each_job = 20*60
+fpga_flow=vpr_blif
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k6_frac_N10_adder_chain_mem16K_40nm_openfpga.xml
+
+[ARCHITECTURES]
+arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_adder_chain_mem16K_reduced_io_40nm.xml
+
+[BENCHMARKS]
+bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.blif
+
+[SYNTHESIS_PARAM]
+bench0_top = top
+bench0_act = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.act
+bench0_verilog = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.v
+bench0_chan_width = 300
+
+[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
+end_flow_with_test=
+vpr_fpga_verilog_formal_verification_top_netlist=

openfpga_flow/tasks/openfpga_shell/mux_design/stdcell_mux2/config/task.conf

@@ -0,0 +1,34 @@
+# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
+# 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
+openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/example_script.openfpga
+power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
+power_analysis = true
+spice_output=false
+verilog_output=true
+timeout_each_job = 20*60
+fpga_flow=vpr_blif
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k6_frac_N10_stdcell_mux_40nm_openfpga.xml
+
+[ARCHITECTURES]
+arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_40nm.xml
+
+[BENCHMARKS]
+bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.blif
+
+[SYNTHESIS_PARAM]
+bench0_top = top
+bench0_act = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.act
+bench0_verilog = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.v
+bench0_chan_width = 300
+
+[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
+end_flow_with_test=
+vpr_fpga_verilog_formal_verification_top_netlist=

openfpga_flow/tasks/openfpga_shell/mux_design/tree_structure/config/task.conf

@@ -0,0 +1,34 @@
+# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
+# 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
+openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/example_script.openfpga
+power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
+power_analysis = true
+spice_output=false
+verilog_output=true
+timeout_each_job = 20*60
+fpga_flow=vpr_blif
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k6_frac_N10_tree_mux_40nm_openfpga.xml
+
+[ARCHITECTURES]
+arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/arch/vpr_only_templates/k6_frac_N10_tileable_40nm.xml
+
+[BENCHMARKS]
+bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.blif
+
+[SYNTHESIS_PARAM]
+bench0_top = top
+bench0_act = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.act
+bench0_verilog = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.v
+bench0_chan_width = 300
+
+[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
+end_flow_with_test=
+vpr_fpga_verilog_formal_verification_top_netlist=

openfpga_flow/tasks/openfpga_shell/untileable/config/task.conf

@@ -0,0 +1,34 @@
+# = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =
+# 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
+openfpga_shell_template=${PATH:OPENFPGA_PATH}/openfpga_flow/OpenFPGAShellScripts/example_script.openfpga
+power_tech_file = ${PATH:OPENFPGA_PATH}/openfpga_flow/tech/PTM_45nm/45nm.xml
+power_analysis = true
+spice_output=false
+verilog_output=true
+timeout_each_job = 20*60
+fpga_flow=vpr_blif
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k6_frac_N10_40nm_openfpga.xml
+
+[ARCHITECTURES]
+arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/arch/vpr_only_templates/k6_frac_N10_40nm.xml
+
+[BENCHMARKS]
+bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.blif
+
+[SYNTHESIS_PARAM]
+bench0_top = top
+bench0_act = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.act
+bench0_verilog = ${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.v
+bench0_chan_width = 300
+
+[SCRIPT_PARAM_MIN_ROUTE_CHAN_WIDTH]
+end_flow_with_test=
+vpr_fpga_verilog_formal_verification_top_netlist=

vpr7_x2p/vpr/SRC/fpga_x2p/module_builder/build_grid_modules.cpp

@@ -292,7 +292,7 @@ void build_primitive_block_module(ModuleManager& module_manager,
   /* Add all the nets to connect configuration ports from memory module to primitive modules
    * This is a one-shot addition that covers all the memory modules in this primitive module!
    */
-  if (false == memory_modules.empty()) {
+  if (0 < module_manager.configurable_children(primitive_module).size()) {
     add_module_nets_memory_config_bus(module_manager, primitive_module, 
                                       sram_orgz_type, circuit_lib.design_tech_type(sram_model));
   }