2 * xxHash - Extremely Fast Hash algorithm
3 * Copyright (C) 2012-2016, Yann Collet.
5 * BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following conditions are
11 * * Redistributions of source code must retain the above copyright
12 * notice, this list of conditions and the following disclaimer.
13 * * Redistributions in binary form must reproduce the above
14 * copyright notice, this list of conditions and the following disclaimer
15 * in the documentation and/or other materials provided with the
18 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
19 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
20 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
21 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
22 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
23 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
24 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
25 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
26 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
27 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
28 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
30 * This program is free software; you can redistribute it and/or modify it under
31 * the terms of the GNU General Public License version 2 as published by the
32 * Free Software Foundation. This program is dual-licensed; you may select
33 * either version 2 of the GNU General Public License ("GPL") or BSD license
36 * You can contact the author at:
37 * - xxHash homepage: https://cyan4973.github.io/xxHash/
38 * - xxHash source repository: https://github.com/Cyan4973/xxHash
42 * Notice extracted from xxHash homepage:
44 * xxHash is an extremely fast Hash algorithm, running at RAM speed limits.
45 * It also successfully passes all tests from the SMHasher suite.
47 * Comparison (single thread, Windows Seven 32 bits, using SMHasher on a Core 2
50 * Name Speed Q.Score Author
52 * CrapWow 3.2 GB/s 2 Andrew
53 * MumurHash 3a 2.7 GB/s 10 Austin Appleby
54 * SpookyHash 2.0 GB/s 10 Bob Jenkins
55 * SBox 1.4 GB/s 9 Bret Mulvey
56 * Lookup3 1.2 GB/s 9 Bob Jenkins
57 * SuperFastHash 1.2 GB/s 1 Paul Hsieh
58 * CityHash64 1.05 GB/s 10 Pike & Alakuijala
59 * FNV 0.55 GB/s 5 Fowler, Noll, Vo
61 * MD5-32 0.33 GB/s 10 Ronald L. Rivest
62 * SHA1-32 0.28 GB/s 10
64 * Q.Score is a measure of quality of the hash function.
65 * It depends on successfully passing SMHasher test set.
66 * 10 is a perfect score.
68 * A 64-bits version, named xxh64 offers much better speed,
69 * but for 64-bits applications only.
70 * Name Speed on 64 bits Speed on 32 bits
71 * xxh64 13.8 GB/s 1.9 GB/s
72 * xxh32 6.8 GB/s 6.0 GB/s
78 #include <linux/types.h>
80 /*-****************************
81 * Simple Hash Functions
82 *****************************/
85 * xxh32() - calculate the 32-bit hash of the input with a given seed.
87 * @input: The data to hash.
88 * @length: The length of the data to hash.
89 * @seed: The seed can be used to alter the result predictably.
91 * Speed on Core 2 Duo @ 3 GHz (single thread, SMHasher benchmark) : 5.4 GB/s
93 * Return: The 32-bit hash of the data.
95 uint32_t xxh32(const void *input, size_t length, uint32_t seed);
98 * xxh64() - calculate the 64-bit hash of the input with a given seed.
100 * @input: The data to hash.
101 * @length: The length of the data to hash.
102 * @seed: The seed can be used to alter the result predictably.
104 * This function runs 2x faster on 64-bit systems, but slower on 32-bit systems.
106 * Return: The 64-bit hash of the data.
108 uint64_t xxh64(const void *input, size_t length, uint64_t seed);
111 * xxhash() - calculate wordsize hash of the input with a given seed
112 * @input: The data to hash.
113 * @length: The length of the data to hash.
114 * @seed: The seed can be used to alter the result predictably.
116 * If the hash does not need to be comparable between machines with
117 * different word sizes, this function will call whichever of xxh32()
118 * or xxh64() is faster.
120 * Return: wordsize hash of the data.
123 static inline unsigned long xxhash(const void *input, size_t length,
126 #if BITS_PER_LONG == 64
127 return xxh64(input, length, seed);
129 return xxh32(input, length, seed);
133 /*-****************************
134 * Streaming Hash Functions
135 *****************************/
138 * These definitions are only meant to allow allocation of XXH state
139 * statically, on stack, or in a struct for example.
140 * Do not use members directly.
144 * struct xxh32_state - private xxh32 state, do not use members directly
147 uint32_t total_len_32;
158 * struct xxh32_state - private xxh64 state, do not use members directly
171 * xxh32_reset() - reset the xxh32 state to start a new hashing operation
173 * @state: The xxh32 state to reset.
174 * @seed: Initialize the hash state with this seed.
176 * Call this function on any xxh32_state to prepare for a new hashing operation.
178 void xxh32_reset(struct xxh32_state *state, uint32_t seed);
181 * xxh32_update() - hash the data given and update the xxh32 state
183 * @state: The xxh32 state to update.
184 * @input: The data to hash.
185 * @length: The length of the data to hash.
187 * After calling xxh32_reset() call xxh32_update() as many times as necessary.
189 * Return: Zero on success, otherwise an error code.
191 int xxh32_update(struct xxh32_state *state, const void *input, size_t length);
194 * xxh32_digest() - produce the current xxh32 hash
196 * @state: Produce the current xxh32 hash of this state.
198 * A hash value can be produced at any time. It is still possible to continue
199 * inserting input into the hash state after a call to xxh32_digest(), and
200 * generate new hashes later on, by calling xxh32_digest() again.
202 * Return: The xxh32 hash stored in the state.
204 uint32_t xxh32_digest(const struct xxh32_state *state);
207 * xxh64_reset() - reset the xxh64 state to start a new hashing operation
209 * @state: The xxh64 state to reset.
210 * @seed: Initialize the hash state with this seed.
212 void xxh64_reset(struct xxh64_state *state, uint64_t seed);
215 * xxh64_update() - hash the data given and update the xxh64 state
216 * @state: The xxh64 state to update.
217 * @input: The data to hash.
218 * @length: The length of the data to hash.
220 * After calling xxh64_reset() call xxh64_update() as many times as necessary.
222 * Return: Zero on success, otherwise an error code.
224 int xxh64_update(struct xxh64_state *state, const void *input, size_t length);
227 * xxh64_digest() - produce the current xxh64 hash
229 * @state: Produce the current xxh64 hash of this state.
231 * A hash value can be produced at any time. It is still possible to continue
232 * inserting input into the hash state after a call to xxh64_digest(), and
233 * generate new hashes later on, by calling xxh64_digest() again.
235 * Return: The xxh64 hash stored in the state.
237 uint64_t xxh64_digest(const struct xxh64_state *state);
239 /*-**************************
241 ***************************/
244 * xxh32_copy_state() - copy the source state into the destination state
246 * @src: The source xxh32 state.
247 * @dst: The destination xxh32 state.
249 void xxh32_copy_state(struct xxh32_state *dst, const struct xxh32_state *src);
252 * xxh64_copy_state() - copy the source state into the destination state
254 * @src: The source xxh64 state.
255 * @dst: The destination xxh64 state.
257 void xxh64_copy_state(struct xxh64_state *dst, const struct xxh64_state *src);
259 #endif /* XXHASH_H */