[WIP] Use KDTree-local compact datastructures

This move the Node informations to dedicated datastructure
decoupling the actor hierarchy from the data allowing using
adapted pattern for both constructing and querying the tree.

kdtree.pyx

@@ -6,11 +6,11 @@ import numpy as np
 np.import_array()
 
 from runtime.runtime cimport BatchMailBox, NullResult, Scheduler, WaitResult
+from libc.math cimport log2, fmax
 from libc.stdio cimport printf
 from libc.stdlib cimport malloc, free
 from openmp cimport omp_get_max_threads
-
-
+from cython.operator cimport dereference as deref
 from cython.parallel import prange
 
 ## Types declaration
@@ -20,6 +20,11 @@ ctypedef double D_t
 cdef lock Scheduler scheduler
 cdef D_t INF = 1e38
 
+cdef struct NodeData_t:
+    I_t idx_start
+    I_t idx_end
+    I_t is_leaf
+
 # NOTE: The following extern definition is used to interface
 # std::nth_element, a robust partitioning algorithm, in Cython
 cdef extern from *:
@@ -339,39 +344,32 @@ cdef cypclass Node activable:
 
     Leafs are terminal Nodes and do not have children.
     """
+    # KDTree pointer reference
+    # TODO: can those be made class attributes?
+    NodeData_t *_node_data_ptr
+    D_t * _node_bounds_ptr
 
     # Reference to the head of the allocated arrays
     # data gets not modified via _data_ptr
-    D_t * _data_ptr
-    I_t * _indices_ptr
-
-    # The point the Node split on
-    D_t * _point
-    I_t _n_dims
-    I_t _dim
-
-    # Portion of _indices covered by the Node is:
-    # _indices_ptr[_start:_end]
-    I_t _start
-    I_t _end
-
-    bint _is_leaf
+    I_t node_index
 
     active Node _left
     active Node _right
 
-    __init__(self):
+    __init__(self, NodeData_t * node_data_ptr, D_t * node_bounds_ptr):
+        # Needed by for Cython+ actors
         self._active_result_class = WaitResult.construct
         self._active_queue_class = consume BatchMailBox(scheduler)
-        self._left = NULL
-        self._right = NULL
-        self._is_leaf = False
+
+        self._node_data_ptr = node_data_ptr
+        self._node_bounds_ptr = node_bounds_ptr
 
 
     # We use this to allow using actors for initialisation
     # because __init__ can't be reified.
     void build_node(
             self,
+            I_t node_index,
             D_t * data_ptr,
             I_t * indices_ptr,
             I_t leaf_size,
@@ -381,20 +379,17 @@ cdef cypclass Node activable:
             I_t end,
             active Counter counter,
     ):
-        cdef I_t i
+        # Simple round-robin on dimensions.
+        # TODO: Choose the dimension with maximum spread at each recursion instead.
         cdef I_t next_dim = (dim + 1) % n_dims
         cdef I_t mid = (start + end) // 2
 
-        self._data_ptr = data_ptr
-        self._indices_ptr = indices_ptr
-
-        self._dim = dim
-        self._n_dims = n_dims
-        self._start = start
-        self._end = end
+        cdef NodeData_t * node_data = self._node_data_ptr + node_index
+        deref(node_data).idx_start = start
+        deref(node_data).idx_end = end
 
         if (end - start <= leaf_size):
-            self._is_leaf = True
+            deref(node_data).is_leaf = True
             # Adding to the global counter the number
             # of samples the leaf is responsible of.
             counter.add(NULL, end - start)
@@ -403,17 +398,16 @@ cdef cypclass Node activable:
         # We partition the samples in two nodes on a given dimension,
         # with the middle point as a pivot.
         partition_node_indices(data_ptr, indices_ptr, start, mid, end, dim, n_dims)
-        self._point = data_ptr + mid
 
-        self._left = consume Node()
-        self._right = consume Node()
+        self._left = consume Node(self._node_data_ptr, self._node_bounds_ptr)
+        self._right = consume Node(self._node_data_ptr, self._node_bounds_ptr)
 
         # Recursing on both partitions.
-        self._left.build_node(NULL,
+        self._left.build_node(NULL, <I_t> 2 * node_index,
                               data_ptr, indices_ptr,
                               leaf_size, n_dims, next_dim,
                               start, mid, counter)
-        self._right.build_node(NULL,
+        self._right.build_node(NULL, <I_t> (2 * node_index + 1),
                                data_ptr, indices_ptr,
                                leaf_size, n_dims, next_dim,
                                mid, end, counter)
@@ -428,21 +422,23 @@ cdef cypclass Node activable:
             D_t dist
             D_t tmp
 
-        if self._is_leaf:
+        if True: #self._is_leaf:
             # Computing all the euclideans distances here.
-            for j in range(self._start, self._end):
-                dist = 0
-                for k in range(self._n_dims):
-                    tmp = (
-                        query_points[i * self._n_dims + k] -
-                        self._data_ptr[self._indices_ptr[j] * self._n_dims + k]
-                        )
-                    dist += tmp * tmp
-
-                # The heap is responsible for keeping the closest
-                # points for each query point i.
-                heaps.push(NULL, i, dist, self._indices_ptr[j])
-
+            # for j in range(self._start, self._end):
+            #     dist = 0
+            #     for k in range(self._n_dims):
+            #         tmp = (
+            #             query_points[i * self._n_dims + k] -
+            #             self._data_ptr[self._indices_ptr[j] * self._n_dims + k]
+            #             )
+            #         dist += tmp * tmp
+            #
+            #
+            #    # The heap is responsible for keeping the closest
+            #    # points for each query point i.
+            #    heaps.push(NULL, i, dist, self._indices_ptr[j])
+            #
+            # return
             return
 
         # TODO: one can implement a pruning strategy here.
@@ -465,6 +461,8 @@ cdef cypclass KDTree:
     I_t _n # number of examples
     I_t _d # number of dimensions / features
     I_t _leaf_size # maximum number of vectors at leaf
+    I_t _n_levels # number of nodes levels in the tree
+    I_t _n_nodes # number of nodes in the tree
 
     I_t _n_leafs
 
@@ -472,6 +470,9 @@ cdef cypclass KDTree:
 
     D_t *_data_ptr
     I_t *_indices_ptr
+    NodeData_t *_node_data_ptr
+    D_t * _node_bounds_ptr
+
 
     __init__(self,
              np.ndarray X,
@@ -492,17 +493,27 @@ cdef cypclass KDTree:
         self._d = d
         self._leaf_size = leaf_size
 
+        self._n_levels = <I_t> (log2(fmax(1, (self._n - 1) / self._leaf_size)) + 1)
+        self._n_nodes = <I_t> (2 ** self._n_levels)
+
         self._data_ptr = <D_t *> X.data
         self._indices_ptr = <I_t *> malloc(n * sizeof(I_t))
+
+        self._node_data_ptr = <NodeData_t *> malloc(self._n_nodes * sizeof(NodeData_t))
+        self._node_bounds_ptr = <D_t *> malloc(2 * self._n_nodes * self._d * sizeof(D_t))
+
         for i in range(n):
             self._indices_ptr[i] = i
 
         # Recurvisely building the tree here
         global scheduler
         scheduler = Scheduler(num_workers)
+
+        # This Counter is used as a way to implement a barrier for
+        # the asynchronous construction of the tree.
         cdef active Counter counter = consume Counter()
 
-        self._root = consume Node()
+        self._root = consume Node(self._node_data_ptr, self._node_bounds_ptr)
         if self._root is NULL:
             printf("Error consuming node\n")
 
@@ -513,7 +524,7 @@ cdef cypclass KDTree:
         #
         # Also using this separate method allowing using actors
         # because __init__ can't be reified.
-        self._root.build_node(NULL,
+        self._root.build_node(NULL, 0,
                               self._data_ptr,
                               self._indices_ptr,
                               self._leaf_size, n_dims=self._d,
@@ -531,6 +542,8 @@ cdef cypclass KDTree:
     void __dealloc__(self):
         scheduler.finish()
         free(self._indices_ptr)
+        free(self._node_data_ptr)
+        free(self._node_bounds_ptr)
 
 
     void query(self,