hashing.hpp
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2019-2023, NVIDIA CORPORATION.
3  *
4  * Licensed under the Apache License, Version 2.0 (the "License");
5  * you may not use this file except in compliance with the License.
6  * You may obtain a copy of the License at
7  *
8  * http://www.apache.org/licenses/LICENSE-2.0
9  *
10  * Unless required by applicable law or agreed to in writing, software
11  * distributed under the License is distributed on an "AS IS" BASIS,
12  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13  * See the License for the specific language governing permissions and
14  * limitations under the License.
15  */
16 #pragma once
17 
18 #include <cudf/table/table.hpp>
20 
22 
23 namespace cudf {
24 
35 using hash_value_type = uint32_t;
36 
41 enum class hash_id {
42  HASH_IDENTITY = 0,
43  HASH_MURMUR3,
44  HASH_SPARK_MURMUR3,
45  HASH_MD5
46 };
47 
51 static constexpr uint32_t DEFAULT_HASH_SEED = 0;
52 
66 std::unique_ptr<column> hash(
67  table_view const& input,
68  hash_id hash_function = hash_id::HASH_MURMUR3,
69  uint32_t seed = DEFAULT_HASH_SEED,
71  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
72 
74 namespace hashing {
75 
90 std::unique_ptr<column> murmurhash3_x86_32(
91  table_view const& input,
92  uint32_t seed = DEFAULT_HASH_SEED,
94  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
95 
109 std::unique_ptr<table> murmurhash3_x64_128(
110  table_view const& input,
111  uint64_t seed = DEFAULT_HASH_SEED,
113  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
114 
128 std::unique_ptr<column> spark_murmurhash3_x86_32(
129  table_view const& input,
130  uint32_t seed = DEFAULT_HASH_SEED,
132  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
133 
143 std::unique_ptr<column> md5(
144  table_view const& input,
146  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
147 
160 std::unique_ptr<column> xxhash_64(
161  table_view const& input,
162  uint64_t seed = DEFAULT_HASH_SEED,
164  rmm::mr::device_memory_resource* mr = rmm::mr::get_current_device_resource());
165 
166 } // namespace hashing
167  // end of group
169 } // namespace cudf
cudf::hashing::md5
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())
Computes the MD5 hash value of each row in the given table.
per_device_resource.hpp
table_view.hpp
Class definitions for (mutable)_table_view
cudf::hashing::xxhash_64
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())
Computes the XXHash_64 hash value of each row in the given table.
rmm::cuda_stream_view
cudf::hashing::murmurhash3_x86_32
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())
Computes the MurmurHash3 32-bit hash value of each row in the given table.
cudf::hashing::spark_murmurhash3_x86_32
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())
Computes the MurmurHash3 32-bit hash value of each row in the given table.
cudf::table_view
A set of cudf::column_view's of the same size.
Definition: table_view.hpp:187
cudf::hash_value_type
uint32_t hash_value_type
Type of hash value.
Definition: hashing.hpp:35
cudf::hashing::murmurhash3_x64_128
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())
Computes the MurmurHash3 64-bit hash value of each row in the given table.
cudf::hash_id
hash_id
Identifies the hash function to be used.
Definition: hashing.hpp:41
cudf
cuDF interfaces
Definition: aggregation.hpp:34
cudf::hash_id::HASH_IDENTITY
@ HASH_IDENTITY
Identity hash function that simply returns the key to be hashed.
cudf::get_default_stream
rmm::cuda_stream_view const get_default_stream()
Get the current default stream.
table.hpp
Class definition for cudf::table.
rmm::mr::device_memory_resource
cudf::hash
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())
Computes the hash value of each row in the input set of columns.