support heterogenous fanout type

cpp/include/cugraph/sampling_functions.hpp

@@ -42,6 +42,8 @@ enum class prior_sources_behavior_t { DEFAULT = 0, CARRY_OVER, EXCLUDE };
 
 /**
  * @brief Uniform Neighborhood Sampling.
+ * 
+ * @deprecated  This API will be deleted, use neighbor_sample instead
  *
  * This function traverses from a set of starting vertices, traversing outgoing edges and
  * randomly selects from these outgoing neighbors to extract a subgraph.
@@ -129,7 +131,7 @@ uniform_neighbor_sample(
   std::optional<raft::device_span<label_t const>> starting_vertex_labels,
   std::optional<std::tuple<raft::device_span<label_t const>, raft::device_span<int32_t const>>>
     label_to_output_comm_rank,
-  raft::host_span<int32_t const> fan_out,
+  std::optional<raft::host_span<int32_t const>> fan_out,
   raft::random::RngState& rng_state,
   bool return_hops,
   bool with_replacement                           = true,
@@ -139,6 +141,8 @@ uniform_neighbor_sample(
 
 /**
  * @brief Biased Neighborhood Sampling.
+ * 
+ * @deprecated  This API will be deleted, use neighbor_sample instead
  *
  * This function traverses from a set of starting vertices, traversing outgoing edges and
  * randomly selects (with edge biases) from these outgoing neighbors to extract a subgraph.
@@ -240,6 +244,116 @@ biased_neighbor_sample(
   bool dedupe_sources                             = false,
   bool do_expensive_check                         = false);
 
+
+/**
+ * @brief Neighborhood Sampling.
+ *
+ * This function traverses from a set of starting vertices, traversing outgoing edges and
+ * randomly selects (with edge biases or not) from these outgoing neighbors to extract a subgraph.
+ *
+ * Output from this function is a tuple of vectors (src, dst, weight, edge_id, edge_type, hop,
+ * label, offsets), identifying the randomly selected edges.  src is the source vertex, dst is the
+ * destination vertex, weight (optional) is the edge weight, edge_id (optional) identifies the edge
+ * id, edge_type (optional) identifies the edge type, hop identifies which hop the edge was
+ * encountered in.  The label output (optional) identifes the vertex label.  The offsets array
+ * (optional) will be described below and is dependent upon the input parameters.
+ *
+ * If @p starting_vertex_labels is not specified then no organization is applied to the output, the
+ * label and offsets values in the return set will be std::nullopt.
+ *
+ * If @p starting_vertex_labels is specified and @p label_to_output_comm_rank is not specified then
+ * the label output has values.  This will also result in the output being sorted by vertex label.
+ * The offsets array in the return will be a CSR-style offsets array to identify the beginning of
+ * each label range in the data.  `labels.size() == (offsets.size() - 1)`.
+ *
+ * If @p starting_vertex_labels is specified and @p label_to_output_comm_rank is specified then the
+ * label output has values.  This will also result in the output being sorted by vertex label.  The
+ * offsets array in the return will be a CSR-style offsets array to identify the beginning of each
+ * label range in the data.  `labels.size() == (offsets.size() - 1)`.  Additionally, the data will
+ * be shuffled so that all data with a particular label will be on the specified rank.
+ *
+ * @tparam vertex_t Type of vertex identifiers. Needs to be an integral type.
+ * @tparam edge_t Type of edge identifiers. Needs to be an integral type.
+ * @tparam weight_t Type of edge weights. Needs to be a floating point type.
+ * @tparam edge_type_t Type of edge type. Needs to be an integral type.
+ * @tparam label_t Type of label. Needs to be an integral type.
+ * @tparam store_transposed Flag indicating whether sources (if false) or destinations (if
+ * true) are major indices
+ * @tparam multi_gpu Flag indicating whether template instantiation should target single-GPU (false)
+ * @param handle RAFT handle object to encapsulate resources (e.g. CUDA stream, communicator, and
+ * handles to various CUDA libraries) to run graph algorithms.
+ * * @param rng_state A pre-initialized raft::RngState object for generating random numbers
+ * @param graph_view Graph View object to generate NBR Sampling on.
+ * @param edge_weight_view Optional view object holding edge weights for @p graph_view.
+ * @param edge_id_view Optional view object holding edge ids for @p graph_view.
+ * @param edge_type_view Optional view object holding edge types for @p graph_view.
+ * @param edge_bias_view Optional view object holding edge biases (to be used in biased sampling) for @p
+ * graph_view. Bias values should be non-negative and the sum of edge bias values from any vertex
+ * should not exceed std::numeric_limits<bias_t>::max(). 0 bias value indicates that the
+ * corresponding edge can never be selected.
+ * @param starting_vertices Device span of starting vertex IDs for the sampling.
+ * In a multi-gpu context the starting vertices should be local to this GPU.
+ * @param starting_vertex_labels Optional device span of labels associted with each starting vertex
+ * for the sampling.
+ * @param label_to_output_comm_rank Optional tuple of device spans mapping label to a particular
+ * output rank.  Element 0 of the tuple identifes the label, Element 1 of the tuple identifies the
+ * output rank.  The label span must be sorted in ascending order.
+ * @param fan_out Host span defining branching out (fan-out) degree per source vertex for each
+ * level
+ * @param heterogeneous_fan_out Tuple of host spans defining branching out (fan-out) degree per
+ * source vertex for each level in CSR style format. The first element of the tuple is the offset
+ * array per edge type id and the second element correspond to the fanout values.
+ * @param return_hops boolean flag specifying if the hop information should be returned
+ * @param prior_sources_behavior Enum type defining how to handle prior sources, (defaults to
+ * DEFAULT)
+ * @param dedupe_sources boolean flag, if true then if a vertex v appears as a destination in hop X
+ * multiple times with the same label, it will only be passed once (for each label) as a source
+ * for the next hop.  Default is false.
+ * @param with_replacement boolean flag specifying if random sampling is done with replacement
+ * (true); or, without replacement (false); default = true;
+ * @param do_expensive_check A flag to run expensive checks for input arguments (if set to `true`).
+ * @return tuple device vectors (vertex_t source_vertex, vertex_t destination_vertex,
+ * optional weight_t weight, optional edge_t edge id, optional edge_type_t edge type,
+ * optional int32_t hop, optional label_t label, optional size_t offsets)
+ */
+// FIXME: Add flag for bias=True/False
+template <typename vertex_t,
+          typename edge_t,
+          typename weight_t,
+          typename edge_type_t,
+          typename bias_t,
+          typename label_t,
+          bool store_transposed,
+          bool multi_gpu>
+std::tuple<rmm::device_uvector<vertex_t>,
+           rmm::device_uvector<vertex_t>,
+           std::optional<rmm::device_uvector<weight_t>>,
+           std::optional<rmm::device_uvector<edge_t>>,
+           std::optional<rmm::device_uvector<edge_type_t>>,
+           std::optional<rmm::device_uvector<int32_t>>,
+           std::optional<rmm::device_uvector<label_t>>,
+           std::optional<rmm::device_uvector<size_t>>>
+neighbor_sample(
+  raft::handle_t const& handle,
+  raft::random::RngState& rng_state,
+  graph_view_t<vertex_t, edge_t, store_transposed, multi_gpu> const& graph_view,
+  std::optional<edge_property_view_t<edge_t, weight_t const*>> edge_weight_view,
+  std::optional<edge_property_view_t<edge_t, edge_t const*>> edge_id_view,
+  std::optional<edge_property_view_t<edge_t, edge_type_t const*>> edge_type_view,
+  std::optional<edge_property_view_t<edge_t, bias_t const*>> edge_bias_view,
+  raft::device_span<vertex_t const> starting_vertices,
+  std::optional<raft::device_span<label_t const>> starting_vertex_labels,
+  std::optional<std::tuple<raft::device_span<label_t const>, raft::device_span<int32_t const>>>
+    label_to_output_comm_rank,
+  std::optional<raft::host_span<int32_t const>> fan_out,
+  std::optional<std::tuple<raft::host_span<int32_t const>, raft::host_span<int32_t const>>>
+    heterogeneous_fan_out,
+  bool return_hops,
+  bool with_replacement                           = true,
+  prior_sources_behavior_t prior_sources_behavior = prior_sources_behavior_t::DEFAULT,
+  bool dedupe_sources                             = false,
+  bool do_expensive_check                         = false);
+
 /*
  * @brief renumber sampled edge list and compress to the (D)CSR|(D)CSC format.
  *

cpp/include/cugraph_c/sampling_algorithms.h

@@ -319,8 +319,59 @@ void cugraph_sampling_set_dedupe_sources(cugraph_sampling_options_t* options, bo
  */
 void cugraph_sampling_options_free(cugraph_sampling_options_t* options);
 
+/**
+ * @brief     Opaque neighborhood sampling heterogeneous fanout type
+ */
+// FIXME: internal representation should be tuple instead of pairs - Make it more generic (tuple)
+// cugraph_device_tuple_t, host_device_tuple_t,
+// dictionary, key and array
+// translate dictionary to a tuple. Add to the draft PR the PLC layer.
+// Concatenate to build the 3 arrays from the PLC layer
+/// mimic
+typedef struct {
+  int32_t align_;
+} cugraph_sample_heterogeneous_fanout_t;
+
+/**
+ * @brief       Create heterogeneous fanout
+ *
+ * Input data will be stored in the heterogenous_fanout.
+ * 
+ * The fanout is going to be a CSR structure, the edge_type_offsets will define which range
+ * of the fanout array is associated with each edge type, the fanout will be the values of
+ * fanout for that hop/type. So for edge type k, fanout[edge_type_offsets[k]] will identify
+ * the fanout for hop 0 for edge type k.  fanout[edge_type_offsets[k] +1] will identify the
+ * fanout for hop 1, etc. edge_type_offsets[k+1] will mark the beginning of the fanout
+ * array for type k+1 (and the end of the fanout array for type k.
+ *
+ * @param [in]  handle         Handle for accessing resources
+ * @param [in]  graph          Pointer to graph
+ * @param [in]  edge_type_offsets Type erased array of edge type offsets
+ * @param [in]  fanout         Type erased array of fanout values
+ * @param [out] heterogeneous_fanout Opaque pointer to fanout_t
+ * @param [out] error          Pointer to an error object storing details of any error.  Will
+ *                             be populated if error code is not CUGRAPH_SUCCESS
+ * @return error code
+ */
+cugraph_error_code_t cugraph_create_heterogeneous_fanout(
+  const cugraph_resource_handle_t* handle,
+  cugraph_graph_t* graph,
+  const cugraph_type_erased_host_array_view_t* edge_type_offsets,
+  const cugraph_type_erased_host_array_view_t* fanout,
+  cugraph_sample_heterogeneous_fanout_t** heterogeneous_fanout,
+  cugraph_error_t** error);
+
+/**
+ * @brief     Free edge type and fanout pairs
+ *
+ * @param [in]    heterogeneous_fanout The edge type size and fanout values
+ */
+void cugraph_heterogeneous_fanout_free(cugraph_sample_heterogeneous_fanout_t* heterogeneous_fanout);
+
 /**
  * @brief     Uniform Neighborhood Sampling
+ * 
+ * @deprecated  This API will be deleted, use cugraph_neighbor_sample instead
  *
  * Returns a sample of the neighborhood around specified start vertices.  Optionally, each
  * start vertex can be associated with a label, allowing the caller to specify multiple batches
@@ -376,6 +427,8 @@ cugraph_error_code_t cugraph_uniform_neighbor_sample(
 
 /**
  * @brief     Biased Neighborhood Sampling
+ * 
+ * @deprecated  This API will be deleted, use cugraph_neighbor_sample instead
  *
  * Returns a sample of the neighborhood around specified start vertices.  Optionally, each
  * start vertex can be associated with a label, allowing the caller to specify multiple batches
@@ -433,6 +486,71 @@ cugraph_error_code_t cugraph_biased_neighbor_sample(
   cugraph_sample_result_t** result,
   cugraph_error_t** error);
 
+/**
+ * @brief     Neighborhood Sampling
+ *
+ * Returns a sample of the neighborhood around specified start vertices with edge biases or not.
+ * Optionally, each start vertex can be associated with a label, allowing the caller to specify
+ * multiple batches of sampling requests in the same function call - which should improve GPU
+ * utilization.
+ *
+ * If label is NULL then all start vertices will be considered part of the same batch and the
+ * return value will not have a label column.
+ *
+ * @param [in]  handle       Handle for accessing resources
+ *  * @param [in,out] rng_state State of the random number generator, updated with each call
+ * @param [in]  graph        Pointer to graph.  NOTE: Graph might be modified if the storage
+ *                           needs to be transposed
+ * @param [in]  edge_biases  Device array of edge biases to use for sampling.  If NULL
+ * use the edge weight as the bias. If set to NULL, edges will be sampled uniformly.
+ * @param [in]  start_vertices Device array of start vertices for the sampling
+ * @param [in]  start_vertex_labels  Device array of start vertex labels for the sampling.  The
+ * labels associated with each start vertex will be included in the output associated with results
+ * that were derived from that start vertex.  We only support label of type INT32. If label is
+ * NULL, the return data will not be labeled.
+ * @param [in]  label_list Device array of the labels included in @p start_vertex_labels.  If
+ * @p label_to_comm_rank is not specified this parameter is ignored.  If specified, label_list
+ * must be sorted in ascending order.
+ * @param [in]  label_to_comm_rank Device array identifying which comm rank the output for a
+ * particular label should be shuffled in the output.  If not specifed the data is not organized in
+ * output.  If specified then the all data from @p label_list[i] will be shuffled to rank @p.  This
+ * cannot be specified unless @p start_vertex_labels is also specified
+ * label_to_comm_rank[i].  If not specified then the output data will not be shuffled between ranks.
+ * @param [in]  label_offsets Device array of the offsets for each label in the seed list.  This
+ *                            parameter is only used with the retain_seeds option.
+ * @param [in]  fanout       Host array defining the fan out at each step in the sampling algorithm.
+ *                           We only support fanout values of type INT32
+ * @param [in]  heterogeneous_fanout  Tuple of host arrays defining the fan out at each step in the
+ * sampling algorithm. in CSR style format. The first element of the tuple is the offset array per
+ * edge type id and the second element correspond to the fanout values.
+ * We only support type INT32 for both the offsets and the fanout values array.
+ * @param [in]  sampling_options
+ *                           Opaque pointer defining the sampling options.
+ * @param [in]  do_expensive_check
+ *                           A flag to run expensive checks for input arguments (if set to true)
+ * @param [out]  result      Output from the uniform_neighbor_sample call
+ * @param [out] error        Pointer to an error object storing details of any error.  Will
+ *                           be populated if error code is not CUGRAPH_SUCCESS
+ * @return error code
+ */
+cugraph_error_code_t cugraph_neighbor_sample(
+  const cugraph_resource_handle_t* handle,
+  cugraph_rng_state_t* rng_state,
+  cugraph_graph_t* graph,
+  bool_t is_biased,
+  const cugraph_edge_property_view_t* edge_biases,
+  const cugraph_type_erased_device_array_view_t* start_vertices,
+  const cugraph_type_erased_device_array_view_t* start_vertex_labels,
+  const cugraph_type_erased_device_array_view_t* label_list,
+  const cugraph_type_erased_device_array_view_t* label_to_comm_rank,
+  const cugraph_type_erased_device_array_view_t* label_offsets,
+  const cugraph_type_erased_host_array_view_t* fan_out,
+  const cugraph_sample_heterogeneous_fanout_t* heterogeneous_fanout,
+  const cugraph_sampling_options_t* options,
+  bool_t do_expensive_check,
+  cugraph_sample_result_t** result,
+  cugraph_error_t** error);
+
 /**
  * @deprecated This call should be replaced with cugraph_sample_result_get_majors
  * @brief     Get the source vertices from the sampling algorithm result
@@ -667,6 +785,7 @@ cugraph_error_code_t cugraph_test_uniform_neighborhood_sample_result_create(
  *                                not CUGRAPH_SUCCESS
  * @return error code
  */
+
 cugraph_error_code_t cugraph_select_random_vertices(const cugraph_resource_handle_t* handle,
                                                     const cugraph_graph_t* graph,
                                                     cugraph_rng_state_t* rng_state,

cpp/src/c_api/array.hpp

@@ -125,6 +125,27 @@ struct cugraph_type_erased_host_array_t {
     std::copy(vec.begin(), vec.end(), reinterpret_cast<T*>(data_.get()));
   }
 
+  cugraph_type_erased_host_array_t(cugraph_type_erased_host_array_view_t const* view_p)
+    : data_(std::make_unique<std::byte[]>(view_p->num_bytes_)),
+      size_(view_p->size_),
+      num_bytes_(view_p->num_bytes_),
+      type_(view_p->type_)
+  {
+    std::copy(view_p->data_, view_p->data_ + num_bytes_, data_.get());
+  }
+
+  template <typename T>
+  T* as_type()
+  {
+    return reinterpret_cast<T*>(data_.get());
+  }
+
+  template <typename T>
+  T const* as_type() const
+  {
+    return reinterpret_cast<T const*>(data_.get());
+  }
+
   auto view()
   {
     return new cugraph_type_erased_host_array_view_t{data_.get(), size_, num_bytes_, type_};

cpp/src/c_api/graph_functions.cpp

@@ -84,7 +84,7 @@ struct create_vertex_pairs_functor : public cugraph::c_api::abstract_functor {
                               std::nullopt,
                               std::nullopt);
       }
-
+      // FIXME: use std::tuple (template) instead.
       result_ = new cugraph::c_api::cugraph_vertex_pairs_t{
         new cugraph::c_api::cugraph_type_erased_device_array_t(first_copy, graph_->vertex_type_),
         new cugraph::c_api::cugraph_type_erased_device_array_t(second_copy, graph_->vertex_type_)};