partitioning.hpp

Go to the documentation of this file.

/*
 * Copyright (c) 2020-2024, NVIDIA CORPORATION.
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
 
#pragma once
 
#include <cudf/hashing.hpp>
#include <cudf/utilities/default_stream.hpp>
#include <cudf/utilities/export.hpp>
#include <cudf/utilities/memory_resource.hpp>
 
#include <rmm/cuda_stream_view.hpp>
 
#include <memory>
#include <vector>
 
namespace CUDF_EXPORT cudf {
enum class hash_id {
  HASH_IDENTITY = 0,  
  HASH_MURMUR3        
};
 
std::pair<std::unique_ptr<table>, std::vector<size_type>> partition(
  table_view const& t,
  column_view const& partition_map,
  size_type num_partitions,
  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
std::pair<std::unique_ptr<table>, std::vector<size_type>> hash_partition(
  table_view const& input,
  std::vector<size_type> const& columns_to_hash,
  int num_partitions,
  hash_id hash_function             = hash_id::HASH_MURMUR3,
  uint32_t seed                     = DEFAULT_HASH_SEED,
  rmm::cuda_stream_view stream      = cudf::get_default_stream(),
  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
std::pair<std::unique_ptr<cudf::table>, std::vector<cudf::size_type>> round_robin_partition(
  table_view const& input,
  cudf::size_type num_partitions,
  cudf::size_type start_partition   = 0,
  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
  // end of group
}  // namespace CUDF_EXPORT cudf