Boost logo

Boost-Commit :

Subject: [Boost-commit] svn:boost r71944 - in sandbox/bloom_filter/branches/prototype: . lib lib/murmurhash3
From: cpp.cabrera_at_[hidden]
Date: 2011-05-14 14:18:23


Author: alejandro
Date: 2011-05-14 14:18:22 EDT (Sat, 14 May 2011)
New Revision: 71944
URL: http://svn.boost.org/trac/boost/changeset/71944

Log:
Prototype implementation of a static bloom filter using std::tuple
and recursive template evaluation to manage all hash function classes.

Added:
   sandbox/bloom_filter/branches/prototype/
   sandbox/bloom_filter/branches/prototype/README (contents, props changed)
   sandbox/bloom_filter/branches/prototype/bloom.hpp (contents, props changed)
   sandbox/bloom_filter/branches/prototype/hash.hpp (contents, props changed)
   sandbox/bloom_filter/branches/prototype/lib/
   sandbox/bloom_filter/branches/prototype/lib/murmurhash3/
   sandbox/bloom_filter/branches/prototype/lib/murmurhash3/MurmurHash3.cpp (contents, props changed)
   sandbox/bloom_filter/branches/prototype/lib/murmurhash3/MurmurHash3.h (contents, props changed)
   sandbox/bloom_filter/branches/prototype/makefile (contents, props changed)
   sandbox/bloom_filter/branches/prototype/test_bloom.cpp (contents, props changed)

Added: sandbox/bloom_filter/branches/prototype/README
==============================================================================
--- (empty file)
+++ sandbox/bloom_filter/branches/prototype/README 2011-05-14 14:18:22 EDT (Sat, 14 May 2011)
@@ -0,0 +1,14 @@
+This prototype uses the public domain library MurmurHash3 to get its
+work done.
+
+To build:
+$> make
+
+To clean:
+$> make clean
+
+To run:
+$> ./test_bloom
+
+-Alejandro Cabrera
+

Added: sandbox/bloom_filter/branches/prototype/bloom.hpp
==============================================================================
--- (empty file)
+++ sandbox/bloom_filter/branches/prototype/bloom.hpp 2011-05-14 14:18:22 EDT (Sat, 14 May 2011)
@@ -0,0 +1,76 @@
+#ifndef _BLOOM_HPP
+#define _BLOOM_HPP 1
+
+#include <bitset>
+#include <tuple>
+#include "hash.hpp"
+
+template <size_t N,
+ typename T,
+ size_t Size,
+ class HashFunctions>
+struct apply_hash
+{
+ static void insert(const T& t, std::bitset<Size>& _bits) {
+ typedef typename std::tuple_element<N, HashFunctions>::type Hash;
+ _bits[Hash::hash(t) % Size] = true;
+ apply_hash<N-1, T, Size, HashFunctions>::insert(t, _bits);
+ }
+
+ static bool contains(const T& t, const std::bitset<Size>& _bits) {
+ typedef typename std::tuple_element<N, HashFunctions>::type Hash;
+ return (_bits[Hash::hash(t) % Size] &&
+ apply_hash<N-1, T, Size, HashFunctions>::contains(t, _bits));
+ }
+};
+
+template <typename T,
+ size_t Size,
+ class HashFunctions>
+struct apply_hash<0, T, Size, HashFunctions>
+{
+ static void insert(const T& t, std::bitset<Size>& _bits) {
+ typedef typename std::tuple_element<0, HashFunctions>::type Hash;
+ _bits[Hash::hash(t) % Size] = true;
+ }
+
+ static bool contains(const T& t, const std::bitset<Size>& _bits) {
+ typedef typename std::tuple_element<0, HashFunctions>::type Hash;
+ return (_bits[Hash::hash(t) % Size]);
+ }
+};
+template <typename T,
+ size_t Size,
+ class HashFunctions = std::tuple<MurmurHash3<T, 3>,
+ MurmurHash3<T, 5>,
+ MurmurHash3<T, 7> > >
+class bloom_filter {
+ typedef std::bitset<Size> Bitset;
+
+public:
+ bloom_filter()
+ {
+ }
+
+ constexpr size_t size() const {
+ return Size;
+ }
+
+ void insert(const T& t) {
+ static const unsigned size = std::tuple_size<HashFunctions>::value - 1;
+ apply_hash<size, T, Size, HashFunctions>::insert(t, bits);
+ }
+
+ bool contains(const T& t) const {
+ static const unsigned size = std::tuple_size<HashFunctions>::value - 1;
+ return apply_hash<size, T, Size, HashFunctions>::contains(t, bits);
+ }
+
+ bool operator[](const T& t) const {
+ return this->contains(t);
+ }
+
+private:
+ std::bitset<Size> bits;
+};
+#endif

Added: sandbox/bloom_filter/branches/prototype/hash.hpp
==============================================================================
--- (empty file)
+++ sandbox/bloom_filter/branches/prototype/hash.hpp 2011-05-14 14:18:22 EDT (Sat, 14 May 2011)
@@ -0,0 +1,98 @@
+#ifndef _HASH_HPP_
+#define _HASH_HPP_ 1
+
+#include <cstdint>
+
+template <typename UnsignedIntT>
+inline UnsignedIntT rotl(const UnsignedIntT x, uint8_t r)
+{
+ return (x << r) | (x >> (sizeof(UnsignedIntT) * 4 - r));
+}
+
+inline uint32_t rotl32(const uint32_t x, uint8_t r)
+{
+ return rotl<uint32_t>(x,r);
+}
+
+inline uint64_t rotl64(const uint64_t x, uint8_t r)
+{
+ return rotl<uint64_t>(x,r);
+}
+
+template <typename UnsignedIntT>
+inline UnsignedIntT get_block(const UnsignedIntT * p, const int i)
+{
+ return p[i];
+}
+
+inline uint32_t fmix(uint32_t h)
+{
+ h ^= h >> 16;
+ h *= 0x85ebca6b;
+ h ^= h >> 13;
+ h *= 0xc2b2ae35;
+ h ^= h >> 16;
+
+ return h;
+}
+
+void murmurhash3(const void *const key, const int len,
+ const uint32_t seed, void *out)
+{
+ static const uint32_t c1 = 0xcc9e2d51;
+ static const uint32_t c2 = 0x1b873593;
+
+ const uint8_t *const data = static_cast<const uint8_t *const>(key);
+
+ uint32_t h1 = seed;
+ const uint32_t *const blocks =
+ reinterpret_cast<const uint32_t *const >(data + len);
+
+ for (int i = -(len/4); i; ++i) {
+ uint32_t k1 = blocks[i];
+
+ k1 *= c1;
+ k1 = rotl32(k1, 15);
+ k1 *= c2;
+
+ h1 ^= k1;
+ h1 = rotl32(h1, 13);
+ h1 = h1*5 + 0xe6546b64;
+ }
+
+ const uint8_t *const tail =
+ static_cast<const uint8_t *const>(data + len);
+
+ uint32_t k1 = 0;
+
+ switch (len & 3) {
+ case 3:
+ k1 ^= tail[2] << 16;
+ case 2:
+ k1 ^= tail[1] << 8;
+ case 1:
+ k1 ^= tail[0];
+ k1 *= c1;
+ k1 = rotl32(k1, 16);
+ k1 *= c2;
+ h1 ^= k1;
+ }
+
+ h1 ^= len;
+ h1 = fmix(h1);
+
+ *static_cast<uint32_t *>(out) = h1;
+}
+
+template <typename T, size_t Seed>
+struct MurmurHash3 {
+ static size_t hash(const T& t) {
+ size_t out = 0;
+ murmurhash3(static_cast<const void *const>(&t),
+ sizeof(t),
+ Seed,
+ &out);
+ return out;
+ }
+};
+#endif

Added: sandbox/bloom_filter/branches/prototype/lib/murmurhash3/MurmurHash3.cpp
==============================================================================
--- (empty file)
+++ sandbox/bloom_filter/branches/prototype/lib/murmurhash3/MurmurHash3.cpp 2011-05-14 14:18:22 EDT (Sat, 14 May 2011)
@@ -0,0 +1,335 @@
+//-----------------------------------------------------------------------------
+// MurmurHash3 was written by Austin Appleby, and is placed in the public
+// domain. The author hereby disclaims copyright to this source code.
+
+// Note - The x86 and x64 versions do _not_ produce the same results, as the
+// algorithms are optimized for their respective platforms. You can still
+// compile and run any of them on any platform, but your performance with the
+// non-native version will be less than optimal.
+
+#include "MurmurHash3.h"
+
+//-----------------------------------------------------------------------------
+// Platform-specific functions and macros
+
+// Microsoft Visual Studio
+
+#if defined(_MSC_VER)
+
+#define FORCE_INLINE __forceinline
+
+#include <stdlib.h>
+
+#define ROTL32(x,y) _rotl(x,y)
+#define ROTL64(x,y) _rotl64(x,y)
+
+#define BIG_CONSTANT(x) (x)
+
+// Other compilers
+
+#else // defined(_MSC_VER)
+
+#define FORCE_INLINE __attribute__((always_inline))
+
+inline uint32_t rotl32 ( uint32_t x, int8_t r )
+{
+ return (x << r) | (x >> (32 - r));
+}
+
+inline uint64_t rotl64 ( uint64_t x, int8_t r )
+{
+ return (x << r) | (x >> (64 - r));
+}
+
+#define ROTL32(x,y) rotl32(x,y)
+#define ROTL64(x,y) rotl64(x,y)
+
+#define BIG_CONSTANT(x) (x##LLU)
+
+#endif // !defined(_MSC_VER)
+
+//-----------------------------------------------------------------------------
+// Block read - if your platform needs to do endian-swapping or can only
+// handle aligned reads, do the conversion here
+
+FORCE_INLINE uint32_t getblock ( const uint32_t * p, int i )
+{
+ return p[i];
+}
+
+FORCE_INLINE uint64_t getblock ( const uint64_t * p, int i )
+{
+ return p[i];
+}
+
+//-----------------------------------------------------------------------------
+// Finalization mix - force all bits of a hash block to avalanche
+
+FORCE_INLINE uint32_t fmix ( uint32_t h )
+{
+ h ^= h >> 16;
+ h *= 0x85ebca6b;
+ h ^= h >> 13;
+ h *= 0xc2b2ae35;
+ h ^= h >> 16;
+
+ return h;
+}
+
+//----------
+
+FORCE_INLINE uint64_t fmix ( uint64_t k )
+{
+ k ^= k >> 33;
+ k *= BIG_CONSTANT(0xff51afd7ed558ccd);
+ k ^= k >> 33;
+ k *= BIG_CONSTANT(0xc4ceb9fe1a85ec53);
+ k ^= k >> 33;
+
+ return k;
+}
+
+//-----------------------------------------------------------------------------
+
+void MurmurHash3_x86_32 ( const void * key, int len,
+ uint32_t seed, void * out )
+{
+ const uint8_t * data = (const uint8_t*)key;
+ const int nblocks = len / 4;
+
+ uint32_t h1 = seed;
+
+ uint32_t c1 = 0xcc9e2d51;
+ uint32_t c2 = 0x1b873593;
+
+ //----------
+ // body
+
+ const uint32_t * blocks = (const uint32_t *)(data + nblocks*4);
+
+ for(int i = -nblocks; i; i++)
+ {
+ uint32_t k1 = getblock(blocks,i);
+
+ k1 *= c1;
+ k1 = ROTL32(k1,15);
+ k1 *= c2;
+
+ h1 ^= k1;
+ h1 = ROTL32(h1,13);
+ h1 = h1*5+0xe6546b64;
+ }
+
+ //----------
+ // tail
+
+ const uint8_t * tail = (const uint8_t*)(data + nblocks*4);
+
+ uint32_t k1 = 0;
+
+ switch(len & 3)
+ {
+ case 3: k1 ^= tail[2] << 16;
+ case 2: k1 ^= tail[1] << 8;
+ case 1: k1 ^= tail[0];
+ k1 *= c1; k1 = ROTL32(k1,16); k1 *= c2; h1 ^= k1;
+ };
+
+ //----------
+ // finalization
+
+ h1 ^= len;
+
+ h1 = fmix(h1);
+
+ *(uint32_t*)out = h1;
+}
+
+//-----------------------------------------------------------------------------
+
+void MurmurHash3_x86_128 ( const void * key, const int len,
+ uint32_t seed, void * out )
+{
+ const uint8_t * data = (const uint8_t*)key;
+ const int nblocks = len / 16;
+
+ uint32_t h1 = seed;
+ uint32_t h2 = seed;
+ uint32_t h3 = seed;
+ uint32_t h4 = seed;
+
+ uint32_t c1 = 0x239b961b;
+ uint32_t c2 = 0xab0e9789;
+ uint32_t c3 = 0x38b34ae5;
+ uint32_t c4 = 0xa1e38b93;
+
+ //----------
+ // body
+
+ const uint32_t * blocks = (const uint32_t *)(data + nblocks*16);
+
+ for(int i = -nblocks; i; i++)
+ {
+ uint32_t k1 = getblock(blocks,i*4+0);
+ uint32_t k2 = getblock(blocks,i*4+1);
+ uint32_t k3 = getblock(blocks,i*4+2);
+ uint32_t k4 = getblock(blocks,i*4+3);
+
+ k1 *= c1; k1 = ROTL32(k1,15); k1 *= c2; h1 ^= k1;
+
+ h1 = ROTL32(h1,19); h1 += h2; h1 = h1*5+0x561ccd1b;
+
+ k2 *= c2; k2 = ROTL32(k2,16); k2 *= c3; h2 ^= k2;
+
+ h2 = ROTL32(h2,17); h2 += h3; h2 = h2*5+0x0bcaa747;
+
+ k3 *= c3; k3 = ROTL32(k3,17); k3 *= c4; h3 ^= k3;
+
+ h3 = ROTL32(h3,15); h3 += h4; h3 = h3*5+0x96cd1c35;
+
+ k4 *= c4; k4 = ROTL32(k4,18); k4 *= c1; h4 ^= k4;
+
+ h4 = ROTL32(h4,13); h4 += h1; h4 = h4*5+0x32ac3b17;
+ }
+
+ //----------
+ // tail
+
+ const uint8_t * tail = (const uint8_t*)(data + nblocks*16);
+
+ uint32_t k1 = 0;
+ uint32_t k2 = 0;
+ uint32_t k3 = 0;
+ uint32_t k4 = 0;
+
+ switch(len & 15)
+ {
+ case 15: k4 ^= tail[14] << 16;
+ case 14: k4 ^= tail[13] << 8;
+ case 13: k4 ^= tail[12] << 0;
+ k4 *= c4; k4 = ROTL32(k4,18); k4 *= c1; h4 ^= k4;
+
+ case 12: k3 ^= tail[11] << 24;
+ case 11: k3 ^= tail[10] << 16;
+ case 10: k3 ^= tail[ 9] << 8;
+ case 9: k3 ^= tail[ 8] << 0;
+ k3 *= c3; k3 = ROTL32(k3,17); k3 *= c4; h3 ^= k3;
+
+ case 8: k2 ^= tail[ 7] << 24;
+ case 7: k2 ^= tail[ 6] << 16;
+ case 6: k2 ^= tail[ 5] << 8;
+ case 5: k2 ^= tail[ 4] << 0;
+ k2 *= c2; k2 = ROTL32(k2,16); k2 *= c3; h2 ^= k2;
+
+ case 4: k1 ^= tail[ 3] << 24;
+ case 3: k1 ^= tail[ 2] << 16;
+ case 2: k1 ^= tail[ 1] << 8;
+ case 1: k1 ^= tail[ 0] << 0;
+ k1 *= c1; k1 = ROTL32(k1,15); k1 *= c2; h1 ^= k1;
+ };
+
+ //----------
+ // finalization
+
+ h1 ^= len; h2 ^= len; h3 ^= len; h4 ^= len;
+
+ h1 += h2; h1 += h3; h1 += h4;
+ h2 += h1; h3 += h1; h4 += h1;
+
+ h1 = fmix(h1);
+ h2 = fmix(h2);
+ h3 = fmix(h3);
+ h4 = fmix(h4);
+
+ h1 += h2; h1 += h3; h1 += h4;
+ h2 += h1; h3 += h1; h4 += h1;
+
+ ((uint32_t*)out)[0] = h1;
+ ((uint32_t*)out)[1] = h2;
+ ((uint32_t*)out)[2] = h3;
+ ((uint32_t*)out)[3] = h4;
+}
+
+//-----------------------------------------------------------------------------
+
+void MurmurHash3_x64_128 ( const void * key, const int len,
+ const uint32_t seed, void * out )
+{
+ const uint8_t * data = (const uint8_t*)key;
+ const int nblocks = len / 16;
+
+ uint64_t h1 = seed;
+ uint64_t h2 = seed;
+
+ uint64_t c1 = BIG_CONSTANT(0x87c37b91114253d5);
+ uint64_t c2 = BIG_CONSTANT(0x4cf5ad432745937f);
+
+ //----------
+ // body
+
+ const uint64_t * blocks = (const uint64_t *)(data);
+
+ for(int i = 0; i < nblocks; i++)
+ {
+ uint64_t k1 = getblock(blocks,i*2+0);
+ uint64_t k2 = getblock(blocks,i*2+1);
+
+ k1 *= c1; k1 = ROTL64(k1,31); k1 *= c2; h1 ^= k1;
+
+ h1 = ROTL64(h1,27); h1 += h2; h1 = h1*5+0x52dce729;
+
+ k2 *= c2; k2 = ROTL64(k2,33); k2 *= c1; h2 ^= k2;
+
+ h2 = ROTL64(h2,31); h2 += h1; h2 = h2*5+0x38495ab5;
+ }
+
+ //----------
+ // tail
+
+ const uint8_t * tail = (const uint8_t*)(data + nblocks*16);
+
+ uint64_t k1 = 0;
+ uint64_t k2 = 0;
+
+ switch(len & 15)
+ {
+ case 15: k2 ^= uint64_t(tail[14]) << 48;
+ case 14: k2 ^= uint64_t(tail[13]) << 40;
+ case 13: k2 ^= uint64_t(tail[12]) << 32;
+ case 12: k2 ^= uint64_t(tail[11]) << 24;
+ case 11: k2 ^= uint64_t(tail[10]) << 16;
+ case 10: k2 ^= uint64_t(tail[ 9]) << 8;
+ case 9: k2 ^= uint64_t(tail[ 8]) << 0;
+ k2 *= c2; k2 = ROTL64(k2,33); k2 *= c1; h2 ^= k2;
+
+ case 8: k1 ^= uint64_t(tail[ 7]) << 56;
+ case 7: k1 ^= uint64_t(tail[ 6]) << 48;
+ case 6: k1 ^= uint64_t(tail[ 5]) << 40;
+ case 5: k1 ^= uint64_t(tail[ 4]) << 32;
+ case 4: k1 ^= uint64_t(tail[ 3]) << 24;
+ case 3: k1 ^= uint64_t(tail[ 2]) << 16;
+ case 2: k1 ^= uint64_t(tail[ 1]) << 8;
+ case 1: k1 ^= uint64_t(tail[ 0]) << 0;
+ k1 *= c1; k1 = ROTL64(k1,31); k1 *= c2; h1 ^= k1;
+ };
+
+ //----------
+ // finalization
+
+ h1 ^= len; h2 ^= len;
+
+ h1 += h2;
+ h2 += h1;
+
+ h1 = fmix(h1);
+ h2 = fmix(h2);
+
+ h1 += h2;
+ h2 += h1;
+
+ ((uint64_t*)out)[0] = h1;
+ ((uint64_t*)out)[1] = h2;
+}
+
+//-----------------------------------------------------------------------------
+

Added: sandbox/bloom_filter/branches/prototype/lib/murmurhash3/MurmurHash3.h
==============================================================================
--- (empty file)
+++ sandbox/bloom_filter/branches/prototype/lib/murmurhash3/MurmurHash3.h 2011-05-14 14:18:22 EDT (Sat, 14 May 2011)
@@ -0,0 +1,37 @@
+//-----------------------------------------------------------------------------
+// MurmurHash3 was written by Austin Appleby, and is placed in the public
+// domain. The author hereby disclaims copyright to this source code.
+
+#ifndef _MURMURHASH3_H_
+#define _MURMURHASH3_H_
+
+//-----------------------------------------------------------------------------
+// Platform-specific functions and macros
+
+// Microsoft Visual Studio
+
+#if defined(_MSC_VER)
+
+typedef unsigned char uint8_t;
+typedef unsigned long uint32_t;
+typedef unsigned __int64 uint64_t;
+
+// Other compilers
+
+#else // defined(_MSC_VER)
+
+#include <stdint.h>
+
+#endif // !defined(_MSC_VER)
+
+//-----------------------------------------------------------------------------
+
+void MurmurHash3_x86_32 ( const void * key, int len, uint32_t seed, void * out );
+
+void MurmurHash3_x86_128 ( const void * key, int len, uint32_t seed, void * out );
+
+void MurmurHash3_x64_128 ( const void * key, int len, uint32_t seed, void * out );
+
+//-----------------------------------------------------------------------------
+
+#endif // _MURMURHASH3_H_

Added: sandbox/bloom_filter/branches/prototype/makefile
==============================================================================
--- (empty file)
+++ sandbox/bloom_filter/branches/prototype/makefile 2011-05-14 14:18:22 EDT (Sat, 14 May 2011)
@@ -0,0 +1,12 @@
+CXXFLAGS := -Wall -Wextra -pedantic -std=c++0x -O3 -g
+ST_LIBS := lib/murmurhash3/MurmurHash3.o
+all : test_bloom
+
+%.o : %.cpp bloom.hpp hash.hpp
+ $(CXX) $(CXXFLAGS) -c $<
+
+test_bloom : test_bloom.o bloom.hpp hash.hpp
+ $(CXX) $(CXXFLAGS) -o $@ $< $(ST_LIBS)
+
+clean:
+ rm -f *.o test_bloom

Added: sandbox/bloom_filter/branches/prototype/test_bloom.cpp
==============================================================================
--- (empty file)
+++ sandbox/bloom_filter/branches/prototype/test_bloom.cpp 2011-05-14 14:18:22 EDT (Sat, 14 May 2011)
@@ -0,0 +1,47 @@
+#include <iostream>
+#include "lib/murmurhash3/MurmurHash3.h"
+#include "bloom.hpp"
+
+typedef int BloomType;
+
+template <typename T, size_t Seed>
+struct OHash {
+ static size_t hash(const T& t) {
+ size_t out = 0;
+ MurmurHash3_x86_32(static_cast<const void *const>(&t),
+ sizeof(t),
+ Seed,
+ &out);
+ return out;
+ }
+};
+
+typedef std::tuple<OHash<BloomType, 2>,
+ OHash<BloomType, 3>,
+ OHash<BloomType, 5>,
+ OHash<BloomType, 7>,
+ OHash<BloomType, 11>,
+ OHash<BloomType, 13>,
+ OHash<BloomType, 17>,
+ OHash<BloomType, 19>> EightHashFunctions_O;
+
+//typedef std::tuple<MurmurHash3<BloomType, 19>> SingleHashFunction;
+
+int main()
+{
+ static const BloomType INSERT_VAL = 100;
+ static const size_t SEARCH_SPACE = 10000000;
+ static const size_t FILTER_SIZE = 64;
+ size_t collisions = 0;
+ bloom_filter<BloomType, FILTER_SIZE, EightHashFunctions_O> bloom;
+
+ std::cout << "bloom size " << sizeof(bloom) << std::endl;
+ bloom.insert(INSERT_VAL);
+ for (size_t i = 0; i < SEARCH_SPACE; ++i) {
+ if (bloom[i] && i != INSERT_VAL) ++collisions;
+ }
+
+ std::cout << collisions << " collisions" << std::endl;
+
+ return 0;
+}


Boost-Commit list run by bdawes at acm.org, david.abrahams at rcn.com, gregod at cs.rpi.edu, cpdaniel at pacbell.net, john at johnmaddock.co.uk