diff --git a/.travis/script.sh b/.travis/script.sh
index 126f633d1..b577ee48c 100755
--- a/.travis/script.sh
+++ b/.travis/script.sh
@@ -48,6 +48,9 @@ python3 openfpga_flow/scripts/run_fpga_task.py duplicate_grid_pin --debug --show
 ##############################################
 echo -e "Testing OpenFPGA Shell";
 
+echo -e "Testing configuration chain of a K4N4 FPGA";
+python3 openfpga_flow/scripts/run_fpga_task.py openfpga_shell/configuration_chain --debug --show_thread_logs
+
 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
 
diff --git a/openfpga/src/fpga_sdc/analysis_sdc_writer_utils.cpp b/openfpga/src/fpga_sdc/analysis_sdc_writer_utils.cpp
index f761cafea..1491d161d 100644
--- a/openfpga/src/fpga_sdc/analysis_sdc_writer_utils.cpp
+++ b/openfpga/src/fpga_sdc/analysis_sdc_writer_utils.cpp
@@ -60,6 +60,7 @@ void disable_analysis_module_input_pin_net_sinks(std::fstream& fp,
 
   /* Find the module net which sources from this port! */
   ModuleNetId module_net = module_manager.module_instance_port_net(parent_module, parent_module, 0, module_input_port, module_input_pin); 
+  if (true != module_manager.valid_module_net_id(parent_module, module_net))
   VTR_ASSERT(true == module_manager.valid_module_net_id(parent_module, module_net));
 
   /* Touch each sink of the net! */
diff --git a/openfpga/src/fpga_verilog/verilog_top_testbench.cpp b/openfpga/src/fpga_verilog/verilog_top_testbench.cpp
index 98d69c337..25017d741 100644
--- a/openfpga/src/fpga_verilog/verilog_top_testbench.cpp
+++ b/openfpga/src/fpga_verilog/verilog_top_testbench.cpp
@@ -273,8 +273,8 @@ void print_verilog_top_testbench_global_ports_stimuli(std::fstream& fp,
       continue;
     }
 
-    /* Bypass gp output signals, they do not need any drivers */
-    if (CIRCUIT_MODEL_PORT_OUTPUT == circuit_lib.port_type(model_global_port)) {
+    /* Bypass io signals, they do not need any drivers */
+    if (true == circuit_lib.port_is_io(model_global_port)) {
       continue;
     }
 
diff --git a/openfpga/src/repack/build_physical_truth_table.cpp b/openfpga/src/repack/build_physical_truth_table.cpp
index 5e291d88b..51fc93f93 100644
--- a/openfpga/src/repack/build_physical_truth_table.cpp
+++ b/openfpga/src/repack/build_physical_truth_table.cpp
@@ -17,6 +17,9 @@
 /* begin namespace openfpga */
 namespace openfpga {
 
+/* Mode 1 is the lut mode while mode 0 is the wire mode */
+constexpr int VPR_PB_TYPE_LUT_MODE = 1;
+
 /***************************************************************************************
  * Identify if LUT is used as wiring 
  * In this case, LUT functions as a buffer
@@ -56,9 +59,23 @@ std::vector<int> generate_lut_rotated_input_pin_map(const std::vector<AtomNetId>
   std::vector<int> rotated_pin_map(input_nets.size(), -1);
 
   VTR_ASSERT(1 == pb_graph_node->num_input_ports);
+
   for (int ipin = 0; ipin < pb_graph_node->num_input_pins[0]; ++ipin) {
+    /* The lut pb_graph_node may not be the primitive node 
+     * because VPR adds two default modes to its LUT pb_type
+     * If so, we will use the LUT mode of the pb_graph node
+     */
+    t_port* lut_pb_type_in_port = pb_graph_node->input_pins[0][ipin].port; 
+    if (0 != pb_graph_node->pb_type->num_modes) {
+      VTR_ASSERT(2 == pb_graph_node->pb_type->num_modes);
+      VTR_ASSERT(1 == pb_graph_node->pb_type->modes[VPR_PB_TYPE_LUT_MODE].num_pb_type_children);
+      lut_pb_type_in_port = &(pb_graph_node->pb_type->modes[VPR_PB_TYPE_LUT_MODE].pb_type_children[0].ports[0]);
+      VTR_ASSERT(std::string(lut_pb_type_in_port->name) == std::string(pb_graph_node->input_pins[0][ipin].port->name));
+      VTR_ASSERT(lut_pb_type_in_port->num_pins == pb_graph_node->input_pins[0][ipin].port->num_pins);
+    }
+
     /* Port exists (some LUTs may have no input and hence no port in the atom netlist) */
-    AtomPortId atom_port = atom_ctx.nlist.find_atom_port(atom_blk, pb_graph_node->input_pins[0][ipin].port->model_port);
+    AtomPortId atom_port = atom_ctx.nlist.find_atom_port(atom_blk, lut_pb_type_in_port->model_port);
     if (!atom_port) { 
       continue;
     }
diff --git a/openfpga_flow/arch/vpr_only_templates/k4_N4_tileable_40nm.xml b/openfpga_flow/arch/vpr_only_templates/k4_N4_tileable_40nm.xml
new file mode 100644
index 000000000..533704db8
--- /dev/null
+++ b/openfpga_flow/arch/vpr_only_templates/k4_N4_tileable_40nm.xml
@@ -0,0 +1,288 @@
+<!-- 
+  Architecture with no fracturable LUTs
+
+  - 40 nm technology
+  - General purpose logic block: 
+    K = 4, N = 4
+  - Routing architecture: L = 4, fc_in = 0.15, Fc_out = 0.1
+
+  Details on Modelling:
+
+  Based on flagship k6_frac_N10_mem32K_40nm.xml architecture.  This architecture has no fracturable LUTs nor any heterogeneous blocks.
+
+
+  Authors: Jason Luu, Jeff Goeders, Vaughn Betz
+-->
+<architecture>
+  <!-- 
+       ODIN II specific config begins 
+       Describes the types of user-specified netlist blocks (in blif, this corresponds to 
+       ".model [type_of_block]") that this architecture supports.
+
+       Note: Basic LUTs, I/Os, and flip-flops are not included here as there are 
+       already special structures in blif (.names, .input, .output, and .latch) 
+       that describe them.
+  -->
+  <models>
+    <!-- A virtual model for I/O to be used in the physical mode of io block -->
+    <model name="io">
+      <input_ports>
+        <port name="outpad"/>
+      </input_ports>
+      <output_ports>
+        <port name="inpad"/>
+      </output_ports>
+    </model>
+  </models>
+  <tiles>
+    <tile name="io" capacity="8" area="0">
+      <equivalent_sites>
+        <site pb_type="io"/>
+      </equivalent_sites>
+      <input name="outpad" num_pins="1"/>
+      <output name="inpad" num_pins="1"/>
+      <fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10"/>
+      <pinlocations pattern="custom">
+        <loc side="left">io.outpad io.inpad</loc>
+        <loc side="top">io.outpad io.inpad</loc>
+        <loc side="right">io.outpad io.inpad</loc>
+        <loc side="bottom">io.outpad io.inpad</loc>
+      </pinlocations>
+    </tile>
+    <tile name="clb" area="53894">
+      <equivalent_sites>
+        <site pb_type="clb"/>
+      </equivalent_sites>
+      <input name="I" num_pins="10" equivalent="full"/>
+      <output name="O" num_pins="4" equivalent="none"/>
+      <clock name="clk" num_pins="1"/>
+      <fc in_type="frac" in_val="0.15" out_type="frac" out_val="0.10"/>
+      <pinlocations pattern="spread"/>
+    </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. -->
+    <segment name="L4" freq="1.000000" length="4" type="unidir" Rmetal="101" Cmetal="22.5e-15">
+      <mux name="0"/>
+      <sb type="pattern">1 1 1 1 1</sb>
+      <cb type="pattern">1 1 1 1</cb>
+    </segment>
+  </segmentlist>
+  <complexblocklist>
+    <!-- Define I/O pads begin -->
+    <!-- Capacity is a unique property of I/Os, it is the maximum number of I/Os that can be placed at the same (X,Y) location on the FPGA -->
+    <!-- Not sure of the area of an I/O (varies widely), and it's not relevant to the design of the FPGA core, so we're setting it to 0. -->
+    <pb_type name="io">
+      <input name="outpad" num_pins="1"/>
+      <output name="inpad" num_pins="1"/>
+      <!-- A mode denotes the physical implementation of an I/O 
+           This mode will be not packable but is mainly used for fabric verilog generation   
+        -->
+      <mode name="physical" 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="10" equivalent="full"/>
+      <output name="O" num_pins="4" equivalent="none"/>
+      <clock name="clk" num_pins="1"/>
+      <!-- Describe basic logic element.  
+             Each basic logic element has a 4-LUT that can be optionally registered
+        -->
+      <pb_type name="fle" num_pb="4">
+        <input name="in" num_pins="4"/>
+        <output name="out" num_pins="1"/>
+        <clock name="clk" num_pins="1"/>
+        <!-- 4-LUT mode definition begin -->
+        <mode name="n1_lut4">
+          <!-- Define 4-LUT mode -->
+          <pb_type name="ble4" num_pb="1">
+            <input name="in" num_pins="4"/>
+            <output name="out" num_pins="1"/>
+            <clock name="clk" num_pins="1"/>
+            <!-- Define LUT -->
+            <pb_type name="lut4" blif_model=".names" num_pb="1" class="lut">
+              <input name="in" num_pins="4" port_class="lut_in"/>
+              <output name="out" num_pins="1" port_class="lut_out"/>
+              <!-- LUT timing using delay matrix -->
+              <delay_matrix type="max" in_port="lut4.in" out_port="lut4.out">
+                261e-12
+                261e-12
+                261e-12
+                261e-12
+              </delay_matrix>
+            </pb_type>
+            <!-- Define flip-flop -->
+            <pb_type name="ff" blif_model=".latch" num_pb="1" class="flipflop">
+              <input name="D" num_pins="1" port_class="D"/>
+              <output name="Q" num_pins="1" port_class="Q"/>
+              <clock name="clk" num_pins="1" port_class="clock"/>
+              <T_setup value="66e-12" port="ff.D" clock="clk"/>
+              <T_clock_to_Q max="124e-12" port="ff.Q" clock="clk"/>
+            </pb_type>
+            <interconnect>
+              <direct name="direct1" input="ble4.in" output="lut4[0:0].in"/>
+              <direct name="direct2" input="lut4.out" output="ff.D">
+                <!-- Advanced user option that tells CAD tool to find LUT+FF pairs in netlist -->
+                <pack_pattern name="ble4" in_port="lut4.out" out_port="ff.D"/>
+              </direct>
+              <direct name="direct3" input="ble4.clk" output="ff.clk"/>
+              <mux name="mux1" input="ff.Q lut4.out" output="ble4.out">
+                <!-- LUT to output is faster than FF to output on a Stratix IV -->
+                <delay_constant max="25e-12" in_port="lut4.out" out_port="ble4.out"/>
+                <delay_constant max="45e-12" in_port="ff.Q" out_port="ble4.out"/>
+              </mux>
+            </interconnect>
+          </pb_type>
+          <interconnect>
+            <direct name="direct1" input="fle.in" output="ble4.in"/>
+            <direct name="direct2" input="ble4.out" output="fle.out[0:0]"/>
+            <direct name="direct3" input="fle.clk" output="ble4.clk"/>
+          </interconnect>
+        </mode>
+        <!-- 6-LUT mode definition end -->
+      </pb_type>
+      <interconnect>
+        <!-- We use a full crossbar to get logical equivalence at inputs of CLB 
+		     The delays below come from Stratix IV. the delay through a connection block
+		     input mux + the crossbar in Stratix IV is 167 ps. We already have a 72 ps 
+		     delay on the connection block input mux (modeled by Ian Kuon), so the remaining
+		     delay within the crossbar is 95 ps. 
+		     The delays of cluster feedbacks in Stratix IV is 100 ps, when driven by a LUT.
+		     Since all our outputs LUT outputs go to a BLE output, and have a delay of 
+		     25 ps to do so, we subtract 25 ps from the 100 ps delay of a feedback
+		     to get the part that should be marked on the crossbar.	 -->
+        <complete name="crossbar" input="clb.I fle[3:0].out" output="fle[3:0].in">
+          <delay_constant max="95e-12" in_port="clb.I" out_port="fle[3:0].in"/>
+          <delay_constant max="75e-12" in_port="fle[3:0].out" out_port="fle[3:0].in"/>
+        </complete>
+        <complete name="clks" input="clb.clk" output="fle[3:0].clk">
+        </complete>
+        <!-- This way of specifying direct connection to clb outputs is important because this architecture uses automatic spreading of opins.  
+               By grouping to output pins in this fashion, if a logic block is completely filled by 6-LUTs, 
+               then the outputs those 6-LUTs take get evenly distributed across all four sides of the CLB instead of clumped on two sides (which is what happens with a more
+               naive specification).
+          -->
+        <direct name="clbouts1" input="fle[3:0].out" output="clb.O"/>
+      </interconnect>
+      <!-- Every input pin is driven by 15% of the tracks in a channel, every output pin is driven by 10% of the tracks in a channel -->
+      <!-- Place this general purpose logic block in any unspecified column -->
+    </pb_type>
+    <!-- Define general purpose logic block (CLB) ends -->
+  </complexblocklist>
+</architecture>
diff --git a/openfpga_flow/arch/vpr_only_templates/k6_N10_40nm.xml b/openfpga_flow/arch/vpr_only_templates/k6_N10_40nm.xml
index 630011e84..e94f339c1 100644
--- a/openfpga_flow/arch/vpr_only_templates/k6_N10_40nm.xml
+++ b/openfpga_flow/arch/vpr_only_templates/k6_N10_40nm.xml
@@ -41,13 +41,12 @@
       </equivalent_sites>
       <input name="outpad" num_pins="1"/>
       <output name="inpad" num_pins="1"/>
-      <clock name="clock" 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 io.clock</loc>
-        <loc side="top">io.outpad io.inpad io.clock</loc>
-        <loc side="right">io.outpad io.inpad io.clock</loc>
-        <loc side="bottom">io.outpad io.inpad io.clock</loc>
+        <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">
@@ -135,7 +134,6 @@
     <pb_type name="io">
       <input name="outpad" num_pins="1"/>
       <output name="inpad" num_pins="1"/>
-      <clock name="clock" num_pins="1"/>
       <!-- A mode denotes the physical implementation of an I/O 
            This mode will be not packable but is mainly used for fabric verilog generation   
         -->
diff --git a/openfpga_flow/arch/vpr_only_templates/k6_N10_tileable_40nm.xml b/openfpga_flow/arch/vpr_only_templates/k6_N10_tileable_40nm.xml
index d86d7aa62..f9065d437 100644
--- a/openfpga_flow/arch/vpr_only_templates/k6_N10_tileable_40nm.xml
+++ b/openfpga_flow/arch/vpr_only_templates/k6_N10_tileable_40nm.xml
@@ -41,13 +41,12 @@
       </equivalent_sites>
       <input name="outpad" num_pins="1"/>
       <output name="inpad" num_pins="1"/>
-      <clock name="clock" 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 io.clock</loc>
-        <loc side="top">io.outpad io.inpad io.clock</loc>
-        <loc side="right">io.outpad io.inpad io.clock</loc>
-        <loc side="bottom">io.outpad io.inpad io.clock</loc>
+        <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">
@@ -135,7 +134,6 @@
     <pb_type name="io">
       <input name="outpad" num_pins="1"/>
       <output name="inpad" num_pins="1"/>
-      <clock name="clock" num_pins="1"/>
       <!-- A mode denotes the physical implementation of an I/O 
            This mode will be not packable but is mainly used for fabric verilog generation   
         -->
diff --git a/openfpga_flow/openfpga_arch/k4_N4_40nm_openfpga.xml b/openfpga_flow/openfpga_arch/k4_N4_40nm_openfpga.xml
new file mode 100644
index 000000000..1d48387ed
--- /dev/null
+++ b/openfpga_flow/openfpga_arch/k4_N4_40nm_openfpga.xml
@@ -0,0 +1,228 @@
+<!-- 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="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" dump_structural_verilog="true">
+      <design_technology type="cmos" structure="multi_level" num_level="2" add_const_input="true" const_input_val="1"/>
+      <input_buffer exist="true" circuit_model_name="INVTX1"/>
+      <output_buffer exist="true" circuit_model_name="INVTX1"/>
+      <pass_gate_logic circuit_model_name="TGATE"/>
+      <port type="input" prefix="in" size="1"/>
+      <port type="output" prefix="out" size="1"/>
+      <port type="sram" prefix="sram" size="1"/>
+    </circuit_model>
+    <circuit_model type="mux" name="mux_2level_tapbuf" prefix="mux_2level_tapbuf" dump_structural_verilog="true">
+      <design_technology type="cmos" structure="multi_level" num_level="2" add_const_input="true" const_input_val="1"/>
+      <input_buffer exist="true" circuit_model_name="INVTX1"/>
+      <output_buffer exist="true" circuit_model_name="tap_buf4"/>
+      <pass_gate_logic circuit_model_name="TGATE"/>
+      <port type="input" prefix="in" size="1"/>
+      <port type="output" prefix="out" size="1"/>
+      <port type="sram" prefix="sram" size="1"/>
+    </circuit_model>
+    <circuit_model type="mux" name="mux_1level_tapbuf" prefix="mux_1level_tapbuf" is_default="true" dump_structural_verilog="true">
+      <design_technology type="cmos" structure="one_level" add_const_input="true" const_input_val="1"/>
+      <input_buffer exist="true" circuit_model_name="INVTX1"/>
+      <output_buffer exist="true" circuit_model_name="tap_buf4"/>
+      <pass_gate_logic circuit_model_name="TGATE"/>
+      <port type="input" prefix="in" size="1"/>
+      <port type="output" prefix="out" size="1"/>
+      <port type="sram" prefix="sram" size="1"/>
+    </circuit_model>
+    <!--DFF subckt ports should be defined as <D> <Q> <CLK> <RESET> <SET>  -->
+    <circuit_model type="ff" name="static_dff" prefix="dff" spice_netlist="${OPENFPGA_PATH}/openfpga_flow/SpiceNetlists/ff.sp" verilog_netlist="${OPENFPGA_PATH}/openfpga_flow/VerilogNetlists/ff.v">
+       <design_technology type="cmos"/>
+       <input_buffer exist="true" circuit_model_name="INVTX1"/>
+       <output_buffer exist="true" circuit_model_name="INVTX1"/>
+       <port type="input" prefix="D" size="1"/>
+       <port type="input" prefix="set" size="1" is_global="true" default_val="0" is_set="true"/>
+       <port type="input" prefix="reset" size="1" is_global="true" default_val="0" is_reset="true"/>
+       <port type="output" prefix="Q" size="1"/>
+       <port type="clock" prefix="clk" size="1" is_global="true" default_val="0" />
+    </circuit_model>
+    <circuit_model type="lut" name="lut4" prefix="lut4" dump_structural_verilog="true">
+      <design_technology type="cmos"/>
+      <input_buffer exist="true" circuit_model_name="INVTX1"/>
+      <output_buffer exist="true" circuit_model_name="INVTX1"/>
+      <lut_input_inverter exist="true" circuit_model_name="INVTX1"/>
+      <lut_input_buffer exist="true" circuit_model_name="buf4"/>
+      <pass_gate_logic circuit_model_name="TGATE"/>
+      <port type="input" prefix="in" size="4"/>
+      <port type="output" prefix="out" size="1"/>
+      <port type="sram" prefix="sram" size="16"/>
+    </circuit_model>
+    <!--Scan-chain DFF subckt ports should be defined as <D> <Q> <Qb> <CLK> <RESET> <SET>  -->
+    <circuit_model type="ccff" name="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[n1_lut4].ble4.lut4" circuit_model_name="lut4"/>
+    <pb_type name="clb.fle[n1_lut4].ble4.ff" circuit_model_name="static_dff"/>
+    <!-- End physical pb_type binding in complex block IO -->
+  </pb_type_annotations>
+</openfpga_architecture>
+<openfpga_simulation_setting>
+  <clock_setting>
+    <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>
diff --git a/openfpga_flow/tasks/openfpga_shell/configuration_chain/config/task.conf b/openfpga_flow/tasks/openfpga_shell/configuration_chain/config/task.conf
index 481faab3a..7415b96ab 100644
--- a/openfpga_flow/tasks/openfpga_shell/configuration_chain/config/task.conf
+++ b/openfpga_flow/tasks/openfpga_shell/configuration_chain/config/task.conf
@@ -15,10 +15,10 @@ spice_output=false
 verilog_output=true
 timeout_each_job = 20*60
 fpga_flow=vpr_blif
-openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k6_frac_N10_40nm_openfpga.xml
+openfpga_arch_file=${PATH:OPENFPGA_PATH}/openfpga_flow/openfpga_arch/k4_N4_40nm_openfpga.xml
 
 [ARCHITECTURES]
-arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/arch/vpr_only_templates/k6_frac_N10_40nm.xml
+arch0=${PATH:OPENFPGA_PATH}/openfpga_flow/arch/vpr_only_templates/k4_N4_tileable_40nm.xml
 
 [BENCHMARKS]
 bench0=${PATH:OPENFPGA_PATH}/openfpga_flow/benchmarks/micro_benchmark/and.blif