Merge pull request #2897 from verilog-to-routing/reconstruction_from_flat_placement_dicrepancy_debugging

Changing subtile selection in the try_centroid_placement of initial_placement

Author: vaughnbetz

vpr/src/place/initial_placement.cpp

@@ -147,6 +147,25 @@ static bool is_loc_legal(const t_pl_loc& loc,
                          const PartitionRegion& pr,
                          t_logical_block_type_ptr block_type);
 
+/**
+ * @brief  Helper function to choose a subtile in specified location if the type is compatible and an available one exists.
+ *  
+ *   @param centroid The centroid location at which the subtile will be selected using its x, y, and layer.
+ *   @param block_type Logical block type we would like to place here.
+ *   @param block_loc_registry Information on where other blocks have been placed.
+ *   @param pr The PartitionRegion of the block we are trying to place - represents its floorplanning constraints; 
+ *   it is the size of the whole chip if the block is not constrained.
+ *   @param rng A random number generator to select a subtile from the available and compatible ones.
+ *
+ * @return True if the location is on the chip, legal, and at least one available subtile is found at that location;
+ * false otherwise.
+ */
+static bool find_subtile_in_location(t_pl_loc& centroid, 
+                             t_logical_block_type_ptr block_type,
+                             const BlkLocRegistry& blk_loc_registry,
+                             const PartitionRegion& pr,
+                             vtr::RngContainer& rng);
+
 /**
  * @brief Calculates a centroid location for a block based on its placed connections.
  *
@@ -340,6 +359,39 @@ static bool is_loc_legal(const t_pl_loc& loc,
     return legal;
 }
 
+bool find_subtile_in_location(t_pl_loc& centroid, 
+                             t_logical_block_type_ptr block_type,
+                             const BlkLocRegistry& blk_loc_registry,
+                             const PartitionRegion& pr,
+                             vtr::RngContainer& rng) {
+    //check if the location is on chip and legal, if yes try to update subtile
+    if (is_loc_on_chip({centroid.x, centroid.y, centroid.layer}) &&  is_loc_legal(centroid, pr, block_type)) {
+        //find the compatible subtiles
+        const auto& device_ctx = g_vpr_ctx.device();
+        const auto& compressed_block_grid = g_vpr_ctx.placement().compressed_block_grids[block_type->index];
+        const auto& type = device_ctx.grid.get_physical_type({centroid.x, centroid.y, centroid.layer});
+        const auto& compatible_sub_tiles = compressed_block_grid.compatible_sub_tile_num(type->index);
+        
+        //filter out the occupied subtiles
+        const GridBlock& grid_blocks = blk_loc_registry.grid_blocks();
+        std::vector<int> available_sub_tiles;
+        available_sub_tiles.reserve(compatible_sub_tiles.size());
+        for (int sub_tile : compatible_sub_tiles) {
+            t_pl_loc pos = {centroid.x, centroid.y, sub_tile, centroid.layer};
+            if (!grid_blocks.block_at_location(pos)) {
+                available_sub_tiles.push_back(sub_tile);
+            }
+        }
+
+        if (!available_sub_tiles.empty()) {
+            centroid.sub_tile = available_sub_tiles[rng.irand((int)available_sub_tiles.size() - 1)];
+            return true;
+        }
+    }
+
+    return false;
+}
+
 static bool find_centroid_neighbor(t_pl_loc& centroid_loc,
                                    t_logical_block_type_ptr block_type,
                                    bool search_for_empty,
@@ -551,10 +603,13 @@ static bool try_centroid_placement(const t_pl_macro& pl_macro,
     t_pl_loc centroid_loc(OPEN, OPEN, OPEN, OPEN);
     std::vector<ClusterBlockId> unplaced_blocks_to_update_their_score;
 
+    bool found_legal_subtile = false;
+
     if (!flat_placement_info.valid) {
         // If a flat placement is not provided, use the centroid of connected
         // blocks which have already been placed.
         unplaced_blocks_to_update_their_score = find_centroid_loc(pl_macro, centroid_loc, blk_loc_registry);
+        found_legal_subtile = find_subtile_in_location(centroid_loc, block_type, blk_loc_registry, pr, rng);
     } else {
         // If a flat placement is provided, use the flat placement to get the
         // centroid.
@@ -567,6 +622,7 @@ static bool try_centroid_placement(const t_pl_macro& pl_macro,
         if (!is_loc_on_chip({centroid_loc.x, centroid_loc.y, centroid_loc.layer}) ||
             !is_loc_legal(centroid_loc, pr, block_type)) {
             unplaced_blocks_to_update_their_score = find_centroid_loc(pl_macro, centroid_loc, blk_loc_registry);
+            found_legal_subtile = find_subtile_in_location(centroid_loc, block_type, blk_loc_registry, pr, rng);
         }
     }
 
@@ -577,9 +633,8 @@ static bool try_centroid_placement(const t_pl_macro& pl_macro,
 
     //centroid suggestion was either occupied or does not match block type
     //try to find a near location that meet these requirements
-    bool neighbor_legal_loc = false;
-    if (!is_loc_legal(centroid_loc, pr, block_type)) {
-        neighbor_legal_loc = find_centroid_neighbor(centroid_loc, block_type, false, blk_loc_registry, rng);
+    if (!found_legal_subtile) {
+        bool neighbor_legal_loc = find_centroid_neighbor(centroid_loc, block_type, false, blk_loc_registry, rng);
         if (!neighbor_legal_loc) { //no neighbor candidate found
             return false;
         }
@@ -591,15 +646,6 @@ static bool try_centroid_placement(const t_pl_macro& pl_macro,
     }
 
     auto& device_ctx = g_vpr_ctx.device();
-    //choose the location's subtile if the centroid location is legal.
-    //if the location is found within the "find_centroid_neighbor", it already has a subtile
-    //we don't need to find one again
-    if (!neighbor_legal_loc) {
-        const auto& compressed_block_grid = g_vpr_ctx.placement().compressed_block_grids[block_type->index];
-        const auto& type = device_ctx.grid.get_physical_type({centroid_loc.x, centroid_loc.y, centroid_loc.layer});
-        const auto& compatible_sub_tiles = compressed_block_grid.compatible_sub_tile_num(type->index);
-        centroid_loc.sub_tile = compatible_sub_tiles[rng.irand((int)compatible_sub_tiles.size() - 1)];
-    }
     int width_offset = device_ctx.grid.get_width_offset({centroid_loc.x, centroid_loc.y, centroid_loc.layer});
     int height_offset = device_ctx.grid.get_height_offset({centroid_loc.x, centroid_loc.y, centroid_loc.layer});
     VTR_ASSERT(width_offset == 0);

vtr_flow/tasks/regression_tests/vtr_reg_multiclock_odin/func_multiclock/blanket/config/golden_results.txt

@@ -1,4 +1,4 @@
 arch	circuit	script_params	vtr_flow_elapsed_time	vtr_max_mem_stage	vtr_max_mem	error	odin_synth_time	max_odin_mem	parmys_synth_time	max_parmys_mem	abc_depth	abc_synth_time	abc_cec_time	abc_sec_time	max_abc_mem	ace_time	max_ace_mem	num_clb	num_io	num_memories	num_mult	vpr_status	vpr_revision	vpr_build_info	vpr_compiler	vpr_compiled	hostname	rundir	max_vpr_mem	num_primary_inputs	num_primary_outputs	num_pre_packed_nets	num_pre_packed_blocks	num_netlist_clocks	num_post_packed_nets	num_post_packed_blocks	device_width	device_height	device_grid_tiles	device_limiting_resources	device_name	pack_mem	pack_time	placed_wirelength_est	place_mem	place_time	place_quench_time	placed_CPD_est	placed_setup_TNS_est	placed_setup_WNS_est	placed_geomean_nonvirtual_intradomain_critical_path_delay_est	place_delay_matrix_lookup_time	place_quench_timing_analysis_time	place_quench_sta_time	place_total_timing_analysis_time	place_total_sta_time	min_chan_width	routed_wirelength	min_chan_width_route_success_iteration	logic_block_area_total	logic_block_area_used	min_chan_width_routing_area_total	min_chan_width_routing_area_per_tile	min_chan_width_route_time	min_chan_width_total_timing_analysis_time	min_chan_width_total_sta_time	crit_path_num_rr_graph_nodes	crit_path_num_rr_graph_edges	crit_path_collapsed_nodes	crit_path_routed_wirelength	crit_path_route_success_iteration	crit_path_total_nets_routed	crit_path_total_connections_routed	crit_path_total_heap_pushes	crit_path_total_heap_pops	crit_path_total_internal_heap_pushes	crit_path_total_internal_heap_pops	crit_path_total_external_heap_pushes	crit_path_total_external_heap_pops	crit_path_total_external_SOURCE_pushes	crit_path_total_external_SOURCE_pops	crit_path_total_internal_SOURCE_pushes	crit_path_total_internal_SOURCE_pops	crit_path_total_external_SINK_pushes	crit_path_total_external_SINK_pops	crit_path_total_internal_SINK_pushes	crit_path_total_internal_SINK_pops	crit_path_total_external_IPIN_pushes	crit_path_total_external_IPIN_pops	crit_path_total_internal_IPIN_pushes	crit_path_total_internal_IPIN_pops	crit_path_total_external_OPIN_pushes	crit_path_total_external_OPIN_pops	crit_path_total_internal_OPIN_pushes	crit_path_total_internal_OPIN_pops	crit_path_total_external_CHANX_pushes	crit_path_total_external_CHANX_pops	crit_path_total_internal_CHANX_pushes	crit_path_total_internal_CHANX_pops	crit_path_total_external_CHANY_pushes	crit_path_total_external_CHANY_pops	crit_path_total_internal_CHANY_pushes	crit_path_total_internal_CHANY_pops	crit_path_rt_node_SOURCE_pushes	crit_path_rt_node_SINK_pushes	crit_path_rt_node_IPIN_pushes	crit_path_rt_node_OPIN_pushes	crit_path_rt_node_CHANX_pushes	crit_path_rt_node_CHANY_pushes	crit_path_adding_all_rt	crit_path_adding_high_fanout_rt	crit_path_total_number_of_adding_all_rt_from_calling_high_fanout_rt	critical_path_delay	geomean_nonvirtual_intradomain_critical_path_delay	setup_TNS	setup_WNS	hold_TNS	hold_WNS	crit_path_routing_area_total	crit_path_routing_area_per_tile	router_lookahead_computation_time	crit_path_route_time	crit_path_create_rr_graph_time	crit_path_create_intra_cluster_rr_graph_time	crit_path_tile_lookahead_computation_time	crit_path_router_lookahead_computation_time	crit_path_total_timing_analysis_time	crit_path_total_sta_time
 k6_frac_N10_mem32K_40nm.xml	multiclock_output_and_latch.v	common	11.99	vpr	255.45 MiB		0.11	36912	-1	-1	1	0.05	-1	-1	34700	-1	-1	2	6	0	0	success	v8.0.0-7653-g7c8f300-dirty	release VTR_ASSERT_LEVEL=3 sanitizers	GNU 9.4.0 on Linux-4.13.1-041301-generic x86_64	2023-04-21 14:13:39	agent-1	/home/mahmo494/RL_experiment/vtr-verilog-to-routing/vtr_flow/tasks	261584	6	1	13	14	2	8	9	4	4	16	clb	auto	101.0 MiB	0.11	13	244.4 MiB	0.04	0	0.875884	-3.21653	-0.875884	0.545	0.47	0.000264546	0.000241337	0.00754986	0.00454282	20	15	7	107788	107788	10441.3	652.579	0.66	0.0136677	0.00891098	742	1670	-1	15	14	32	32	476	268	0	0	476	268	32	32	0	0	45	42	0	0	51	45	0	0	32	32	0	0	205	79	0	0	111	38	0	0	32	0	0	0	0	0	32	0	0	1.31811	0.545	-4.12048	-1.31811	0	0	13748.8	859.301	0.01	0.04	0.18	-1	-1	0.01	0.00722654	0.00593545
 k6_frac_N10_mem32K_40nm.xml	multiclock_reader_writer.v	common	12.96	vpr	261.56 MiB		0.15	45980	-1	-1	1	0.06	-1	-1	34932	-1	-1	2	3	0	0	success	v8.0.0-7653-g7c8f300-dirty	release VTR_ASSERT_LEVEL=3 sanitizers	GNU 9.4.0 on Linux-4.13.1-041301-generic x86_64	2023-04-21 14:13:39	agent-1	/home/mahmo494/RL_experiment/vtr-verilog-to-routing/vtr_flow/tasks	267836	3	1	25	26	2	8	6	4	4	16	clb	auto	106.4 MiB	0.87	17	249.9 MiB	0.03	0	0.571	-8.64803	-0.571	0.557849	0.47	0.000543454	0.000488368	0.00346482	0.00253954	20	19	1	107788	107788	10441.3	652.579	0.67	0.0113116	0.00855232	742	1670	-1	27	1	6	6	63	36	0	0	63	36	6	6	0	0	9	6	0	0	9	9	0	0	6	6	0	0	18	3	0	0	15	6	0	0	6	0	0	0	0	0	6	0	0	0.865	0.557849	-8.82275	-0.865	0	0	13748.8	859.301	0.01	0.04	0.17	-1	-1	0.01	0.00501901	0.00409753
-k6_frac_N10_mem32K_40nm.xml	multiclock_separate_and_latch.v	common	11.88	vpr	254.22 MiB		0.15	35980	-1	-1	1	0	-1	-1	32420	-1	-1	2	6	0	0	success	v8.0.0-7653-g7c8f300-dirty	release VTR_ASSERT_LEVEL=3 sanitizers	GNU 9.4.0 on Linux-4.13.1-041301-generic x86_64	2023-04-21 14:13:39	agent-1	/home/mahmo494/RL_experiment/vtr-verilog-to-routing/vtr_flow/tasks	260320	6	2	10	12	2	8	10	4	4	16	clb	auto	100.4 MiB	0.06	12	243.6 MiB	0.03	0	0.544641	-1.83465	-0.544641	nan	0.47	0.000504445	0.000240584	0.00477542	0.00228264	20	15	1	107788	107788	10441.3	652.579	0.64	0.00804976	0.00416003	742	1670	-1	13	1	6	6	148	96	0	0	148	96	6	6	0	0	18	16	0	0	18	18	0	0	6	6	0	0	53	27	0	0	47	23	0	0	6	0	0	0	0	0	6	0	0	0.81248	nan	-2.54321	-0.81248	0	0	13748.8	859.301	0.01	0.02	0.18	-1	-1	0.01	0.00215701	0.00121245
+k6_frac_N10_mem32K_40nm.xml	multiclock_separate_and_latch.v	common	11.88	vpr	254.22 MiB		0.15	35980	-1	-1	1	0	-1	-1	32420	-1	-1	2	6	0	0	success	v8.0.0-7653-g7c8f300-dirty	release VTR_ASSERT_LEVEL=3 sanitizers	GNU 9.4.0 on Linux-4.13.1-041301-generic x86_64	2023-04-21 14:13:39	agent-1	/home/mahmo494/RL_experiment/vtr-verilog-to-routing/vtr_flow/tasks	260320	6	2	10	12	2	8	10	4	4	16	clb	auto	100.4 MiB	0.06	12	243.6 MiB	0.03	0	0.544641	-1.83465	-0.544641	nan	0.47	0.000504445	0.000240584	0.00477542	0.00228264	20	27	1	107788	107788	10441.3	652.579	0.64	0.00804976	0.00416003	742	1670	-1	13	1	6	6	148	96	0	0	148	96	6	6	0	0	18	16	0	0	18	18	0	0	6	6	0	0	53	27	0	0	47	23	0	0	6	0	0	0	0	0	6	0	0	0.81248	nan	-2.54321	-0.81248	0	0	13748.8	859.301	0.01	0.02	0.18	-1	-1	0.01	0.00215701	0.00121245