[Router] Finally fixed the weird bug in parallel connection router

Fixed the weird bug in parallel connection router as mentioned in commit
f73212c. The bug occurred because two function parameters 'num_threads'
and 'num_queues' have been misplaced when instantiating the MQ_IO. This
took two weeks to figure out exactly.

The VTR benchmark (`vtr_reg_qor_chain` task) has been tested/passed for
different cases (1) 'serial mode' 1T+2Q (1 thread, 2 queues), (2) 2T+4Q,
and (3) 4T+2Q.

The determinism has also been verified for the VTR benchmark.

Author: ueqri

vpr/src/route/multi_queue_d_ary_heap.h

@@ -41,7 +41,7 @@ class MultiQueueDAryHeap {
     using MQ_IO = MultiQueueIO<D, MQHeapNode, MQHeapNodeTupleComparator, HeapNodePriority>;
 
     MultiQueueDAryHeap() {
-        set_num_threads_and_queues(2, 1); // Serial (#threads=1, #queues=2) by default
+        set_num_threads_and_queues(1, 2); // Serial (#threads=1, #queues=2) by default
     }
 
     MultiQueueDAryHeap(size_t num_threads, size_t num_queues) {
@@ -52,7 +52,8 @@ class MultiQueueDAryHeap {
 
     void set_num_threads_and_queues(size_t num_threads, size_t num_queues) {
         pq_.reset();
-        pq_ = std::make_unique<MQ_IO>(num_threads, num_queues, 0 /*Dont care (batch size for only popBatch)*/);
+        // Note: BE AWARE that in MQ_IO interface, `num_queues` comes first, then `num_threads`!
+        pq_ = std::make_unique<MQ_IO>(num_queues, num_threads, 0 /*Dont care (batch size for only popBatch)*/);
     }
 
     void init_heap(const DeviceGrid& grid) {

vpr/src/route/parallel_connection_router.h

@@ -207,13 +207,9 @@ class ParallelConnectionRouter : public ConnectionRouter<MultiQueueDAryHeap<Heap
      * @brief Resets modified data in rr_node_route_inf based on modified_rr_node_inf
      */
     void reset_path_costs() final {
-        auto& route_ctx = g_vpr_ctx.mutable_routing();
+        // Reset the node info stored in rr_node_route_inf variable
         for (const auto& thread_visited_rr_nodes : this->modified_rr_node_inf_) {
-            for (const auto node : thread_visited_rr_nodes) {
-                route_ctx.rr_node_route_inf[node].path_cost = std::numeric_limits<float>::infinity();
-                route_ctx.rr_node_route_inf[node].backward_path_cost = std::numeric_limits<float>::infinity();
-                route_ctx.rr_node_route_inf[node].prev_edge = RREdgeId::INVALID();
-            }
+            ::reset_path_costs(thread_visited_rr_nodes);
         }
     }