Merge pull request #3137 from verilog-to-routing/ap_high_fanout_net_thresholding

High Fanout Net Thresholding in AP to Speed Up Solver

Author: AlexandreSinger

doc/src/vpr/command_line_usage.rst

@@ -1324,6 +1324,14 @@ Analytical Placement is generally split into three stages:
 
     **Default:** ``auto``
 
+.. option:: --ap_high_fanout_threshold <int>
+
+    Defines the threshold for high fanout nets within AP flow.
+
+    Ignores the nets that have higher fanouts than the threshold for the analytical solver.
+
+    **Default:** ``256``
+
 .. option:: --ap_verbosity <int>
 
     Controls the verbosity of the AP flow output.

vpr/src/analytical_place/analytical_placement_flow.cpp

@@ -170,6 +170,7 @@ void run_analytical_placement_flow(t_vpr_setup& vpr_setup) {
     const AtomNetlist& atom_nlist = g_vpr_ctx.atom().netlist();
     const DeviceContext& device_ctx = g_vpr_ctx.device();
     const UserPlaceConstraints& constraints = g_vpr_ctx.floorplanning().constraints;
+    const t_ap_opts& ap_opts = vpr_setup.APOpts;
 
     // Run the prepacker
     const Prepacker prepacker(atom_nlist, device_ctx.arch->models, device_ctx.logical_block_types);
@@ -178,7 +179,8 @@ void run_analytical_placement_flow(t_vpr_setup& vpr_setup) {
     // prepacker.
     APNetlist ap_netlist = gen_ap_netlist_from_atoms(atom_nlist,
                                                      prepacker,
-                                                     constraints);
+                                                     constraints,
+                                                     ap_opts.ap_high_fanout_threshold);
     print_ap_netlist_stats(ap_netlist);
 
     // Pre-compute the pre-clustering timing delays. This object will be passed
@@ -208,7 +210,6 @@ void run_analytical_placement_flow(t_vpr_setup& vpr_setup) {
     }
 
     // Run the Global Placer.
-    const t_ap_opts& ap_opts = vpr_setup.APOpts;
     PartialPlacement p_placement = run_global_placer(ap_opts,
                                                      atom_nlist,
                                                      ap_netlist,

vpr/src/analytical_place/gen_ap_netlist_from_atoms.cpp

@@ -24,7 +24,8 @@
 
 APNetlist gen_ap_netlist_from_atoms(const AtomNetlist& atom_netlist,
                                     const Prepacker& prepacker,
-                                    const UserPlaceConstraints& constraints) {
+                                    const UserPlaceConstraints& constraints,
+                                    int high_fanout_threshold) {
     // Create a scoped timer for reading the atom netlist.
     vtr::ScopedStartFinishTimer timer("Read Atom Netlist to AP Netlist");
 
@@ -115,6 +116,7 @@ APNetlist gen_ap_netlist_from_atoms(const AtomNetlist& atom_netlist,
     //  - a global net
     //  - connected to 1 or fewer unique blocks
     //  - connected to only fixed blocks
+    //  - having fanout higher than threshold
     for (APNetId ap_net_id : ap_netlist.nets()) {
         // Is the net ignored for placement, if so mark as ignored for AP.
         const std::string& net_name = ap_netlist.net_name(ap_net_id);
@@ -153,6 +155,13 @@ APNetlist gen_ap_netlist_from_atoms(const AtomNetlist& atom_netlist,
             ap_netlist.set_net_is_ignored(ap_net_id, true);
             continue;
         }
+        // If fanout number of the net is higher than the threshold, mark as ignored for AP.
+        size_t num_pins = ap_netlist.net_pins(ap_net_id).size();
+        VTR_ASSERT_DEBUG(num_pins > 1);
+        if (num_pins - 1 > static_cast<size_t>(high_fanout_threshold)) {
+            ap_netlist.set_net_is_ignored(ap_net_id, true);
+            continue;
+        }
     }
     ap_netlist.compress();
 

vpr/src/analytical_place/gen_ap_netlist_from_atoms.h

@@ -16,13 +16,16 @@ class UserPlaceConstraints;
 /**
  * @brief Use the results from prepacking the atom netlist to generate an APNetlist.
  *
- *  @param atom_netlist The atom netlist for the input design.
- *  @param prepacker    The prepacker, initialized on the provided atom netlist.
- *  @param constraints  The placement constraints on the Atom blocks, provided
- *                      by the user.
+ *  @param atom_netlist          The atom netlist for the input design.
+ *  @param prepacker             The prepacker, initialized on the provided atom netlist.
+ *  @param constraints           The placement constraints on the Atom blocks, provided
+ *                               by the user.
+ *  @param high_fanout_threshold The threshold above which nets with higher fanout will
+ *                               be ignored.
  *
  *  @return             An APNetlist object, generated from the prepacker results.
  */
 APNetlist gen_ap_netlist_from_atoms(const AtomNetlist& atom_netlist,
                                     const Prepacker& prepacker,
-                                    const UserPlaceConstraints& constraints);
+                                    const UserPlaceConstraints& constraints,
+                                    int high_fanout_threshold);

vpr/src/base/CheckSetup.cpp

@@ -88,6 +88,12 @@ void CheckSetup(const t_packer_opts& packer_opts,
                             "ap_timing_tradeoff expects a value between 0.0 and 1.0");
         }
 
+        // Make sure that the high fanout threshold for solver is valid.
+        if (ap_opts.ap_high_fanout_threshold <= 1) {
+            VPR_FATAL_ERROR(VPR_ERROR_OTHER,
+                            "ap_high_fanout_threshold should be greater than 1");
+        }
+
         // TODO: Should we enforce that the size of the device is fixed. This
         //       goes with ensuring that some blocks are fixed.
     }

vpr/src/base/SetupVPR.cpp

@@ -558,6 +558,7 @@ void SetupAPOpts(const t_options& options,
     apOpts.full_legalizer_type = options.ap_full_legalizer.value();
     apOpts.detailed_placer_type = options.ap_detailed_placer.value();
     apOpts.ap_timing_tradeoff = options.ap_timing_tradeoff.value();
+    apOpts.ap_high_fanout_threshold = options.ap_high_fanout_threshold.value();
     apOpts.appack_max_dist_th = options.appack_max_dist_th.value();
     apOpts.num_threads = options.num_workers.value();
     apOpts.log_verbosity = options.ap_verbosity.value();

vpr/src/base/ShowSetup.cpp

@@ -656,6 +656,7 @@ static void ShowAnalyticalPlacerOpts(const t_ap_opts& APOpts) {
     }
 
     VTR_LOG("AnalyticalPlacerOpts.ap_timing_tradeoff: %f\n", APOpts.ap_timing_tradeoff);
+    VTR_LOG("AnalyticalPlacerOpts.ap_high_fanout_threshold: %d\n", APOpts.ap_high_fanout_threshold);
     VTR_LOG("AnalyticalPlacerOpts.log_verbosity: %d\n", APOpts.log_verbosity);
 }
 

vpr/src/base/read_options.cpp

@@ -1950,6 +1950,13 @@ argparse::ArgumentParser create_arg_parser(const std::string& prog_name, t_optio
         .default_value("0.5")
         .show_in(argparse::ShowIn::HELP_ONLY);
 
+    ap_grp.add_argument<int>(args.ap_high_fanout_threshold, "--ap_high_fanout_threshold")
+        .help(
+            "Defines the threshold for high fanout nets within AP flow.\n"
+            "Ignores the nets that have higher fanouts than the threshold for the analytical solver.")
+        .default_value("256")
+        .show_in(argparse::ShowIn::HELP_ONLY);
+
     ap_grp.add_argument(args.appack_max_dist_th, "--appack_max_dist_th")
         .help(
             "Sets the maximum candidate distance thresholds for the logical block types"

vpr/src/base/read_options.h

@@ -106,6 +106,7 @@ struct t_options {
     argparse::ArgValue<std::vector<std::string>> appack_max_dist_th;
     argparse::ArgValue<int> ap_verbosity;
     argparse::ArgValue<float> ap_timing_tradeoff;
+    argparse::ArgValue<int> ap_high_fanout_threshold;
     argparse::ArgValue<bool> ap_generate_mass_report;
 
     /* Clustering options */

vpr/src/base/vpr_types.h

@@ -1102,6 +1102,9 @@ struct t_placer_opts {
  *   @param ap_timing_tradeoff
  *              A trade-off parameter used to decide how focused the AP flow
  *              should be on optimizing timing over wirelength.
+ *   @param ap_high_fanout_threshold;
+ *              The threshold to ignore nets with higher fanout than that
+ *              value while constructing the solver.
  *   @param appack_max_dist_th
  *              Array of string passed by the user to configure the max candidate
  *              distance thresholds.
@@ -1126,6 +1129,8 @@ struct t_ap_opts {
 
     float ap_timing_tradeoff;
 
+    int ap_high_fanout_threshold;
+
     std::vector<std::string> appack_max_dist_th;
 
     unsigned num_threads;