hashing.hpp
Go to the documentation of this file.
1 /*
2  * Copyright (c) 2019-2024, 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 #include <cudf/utilities/export.hpp>
22 
23 namespace CUDF_EXPORT cudf {
24 
29 using hash_value_type = uint32_t;
30 
35 static constexpr uint32_t DEFAULT_HASH_SEED = 0;
36 
38 namespace hashing {
39 
60 std::unique_ptr<column> murmurhash3_x86_32(
61  table_view const& input,
62  uint32_t seed = DEFAULT_HASH_SEED,
65 
79 std::unique_ptr<table> murmurhash3_x64_128(
80  table_view const& input,
81  uint64_t seed = DEFAULT_HASH_SEED,
84 
94 std::unique_ptr<column> md5(
95  table_view const& input,
98 
108 std::unique_ptr<column> sha1(
109  table_view const& input,
112 
122 std::unique_ptr<column> sha224(
123  table_view const& input,
126 
136 std::unique_ptr<column> sha256(
137  table_view const& input,
140 
150 std::unique_ptr<column> sha384(
151  table_view const& input,
154 
164 std::unique_ptr<column> sha512(
165  table_view const& input,
168 
181 std::unique_ptr<column> xxhash_64(
182  table_view const& input,
183  uint64_t seed = DEFAULT_HASH_SEED,
186  // end of group
188 
189 } // namespace hashing
190 
191 } // namespace CUDF_EXPORT cudf
A set of cudf::column_view's of the same size.
Definition: table_view.hpp:200
std::unique_ptr< column > sha512(table_view const &input, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Computes the SHA-512 hash value of each row in the given table.
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::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Computes the MurmurHash3 32-bit hash value of each row in the given table.
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::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Computes the XXHash_64 hash value of each row in the given table.
std::unique_ptr< column > sha224(table_view const &input, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Computes the SHA-224 hash value of each row in the given table.
std::unique_ptr< column > sha256(table_view const &input, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Computes the SHA-256 hash value of each row in the given table.
uint32_t hash_value_type
Type of hash value.
Definition: hashing.hpp:29
std::unique_ptr< column > md5(table_view const &input, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Computes the MD5 hash value of each row in the given table.
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::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Computes the MurmurHash3 64-bit hash value of each row in the given table.
std::unique_ptr< column > sha1(table_view const &input, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Computes the SHA-1 hash value of each row in the given table.
std::unique_ptr< column > sha384(table_view const &input, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref())
Computes the SHA-384 hash value of each row in the given table.
rmm::cuda_stream_view const get_default_stream()
Get the current default stream.
rmm::device_async_resource_ref get_current_device_resource_ref()
Get the current device memory resource reference.
cuda::mr::async_resource_ref< cuda::mr::device_accessible > device_async_resource_ref
cuDF interfaces
Definition: host_udf.hpp:39
Class definition for cudf::table.
Class definitions for (mutable)_table_view