hashing.hpp

Go to the documentation of this file.

/*
 * Copyright (c) 2019-2024, 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/table/table.hpp>
#include <cudf/table/table_view.hpp>
 
#include <rmm/mr/device/per_device_resource.hpp>
 
namespace cudf {
 
using hash_value_type = uint32_t;
 
enum class hash_id {
  HASH_IDENTITY = 0,   
  HASH_MURMUR3,        
  HASH_SPARK_MURMUR3,  
  HASH_MD5             
};
 
static constexpr uint32_t DEFAULT_HASH_SEED = 0;
 
std::unique_ptr<column> hash(
  table_view const& input,
  hash_id hash_function               = hash_id::HASH_MURMUR3,
  uint32_t seed                       = DEFAULT_HASH_SEED,
  rmm::cuda_stream_view stream        = cudf::get_default_stream(),
  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
namespace hashing {
 
std::unique_ptr<column> murmurhash3_x86_32(
  table_view const& input,
  uint32_t seed                       = DEFAULT_HASH_SEED,
  rmm::cuda_stream_view stream        = cudf::get_default_stream(),
  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
std::unique_ptr<table> murmurhash3_x64_128(
  table_view const& input,
  uint64_t seed                       = DEFAULT_HASH_SEED,
  rmm::cuda_stream_view stream        = cudf::get_default_stream(),
  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
std::unique_ptr<column> spark_murmurhash3_x86_32(
  table_view const& input,
  uint32_t seed                       = DEFAULT_HASH_SEED,
  rmm::cuda_stream_view stream        = cudf::get_default_stream(),
  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
std::unique_ptr<column> md5(
  table_view const& input,
  rmm::cuda_stream_view stream        = cudf::get_default_stream(),
  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
std::unique_ptr<column> sha1(
  table_view const& input,
  rmm::cuda_stream_view stream        = cudf::get_default_stream(),
  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
std::unique_ptr<column> sha224(
  table_view const& input,
  rmm::cuda_stream_view stream        = cudf::get_default_stream(),
  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
std::unique_ptr<column> sha256(
  table_view const& input,
  rmm::cuda_stream_view stream        = cudf::get_default_stream(),
  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
std::unique_ptr<column> sha384(
  table_view const& input,
  rmm::cuda_stream_view stream        = cudf::get_default_stream(),
  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
std::unique_ptr<column> sha512(
  table_view const& input,
  rmm::cuda_stream_view stream        = cudf::get_default_stream(),
  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
std::unique_ptr<column> xxhash_64(
  table_view const& input,
  uint64_t seed                       = DEFAULT_HASH_SEED,
  rmm::cuda_stream_view stream        = cudf::get_default_stream(),
  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
 
}  // namespace hashing
  // end of group
}  // namespace cudf