diff --git a/Dish.cabal b/Dish.cabal new file mode 100644 --- /dev/null +++ b/Dish.cabal @@ -0,0 +1,30 @@ +name: Dish +version: 0.0.0.1 +homepage: http://github.com/zcourts/Dish +license: BSD3 +license-file: LICENSE +author: Courtney Robinson +maintainer: oss@crlog.info +category: Data +build-type: Simple +cabal-version: >=1.8 +--extra-source-files: cbits/murmur3.c, cbits/murmur3.h +description: A group of Hash related utilities (currently wraps MurmurHash3 C implementation) +synopsis: Hash modules (currently Murmur3) + +source-repository head + type: git + location: https://github.com/zcourts/Dish.git + +library + build-depends: + base >=4.6.0 && <4.7, + bytestring >=0.10.0 && <0.11 + hs-source-dirs: src + c-sources: cbits/murmur3.c + include-dirs: cbits + extra-libraries: + --cc-options: -O3 + extensions: ForeignFunctionInterface + other-modules: + exposed-modules: Data.Dish.Murmur3 diff --git a/LICENSE b/LICENSE new file mode 100644 --- /dev/null +++ b/LICENSE @@ -0,0 +1,30 @@ +Copyright (c) 2014, Courtney Robinson + +All rights reserved. + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions are met: + + * Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + + * Redistributions in binary form must reproduce the above + copyright notice, this list of conditions and the following + disclaimer in the documentation and/or other materials provided + with the distribution. + + * Neither the name of Courtney Robinson nor the names of other + contributors may be used to endorse or promote products derived + from this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. diff --git a/Setup.hs b/Setup.hs new file mode 100644 --- /dev/null +++ b/Setup.hs @@ -0,0 +1,2 @@ +import Distribution.Simple +main = defaultMain diff --git a/cbits/murmur3.c b/cbits/murmur3.c new file mode 100644 --- /dev/null +++ b/cbits/murmur3.c @@ -0,0 +1,315 @@ +//----------------------------------------------------------------------------- +// 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 "murmur3.h" + +//----------------------------------------------------------------------------- +// Platform-specific functions and macros + +#ifdef __GNUC__ +#define FORCE_INLINE __attribute__((always_inline)) inline +#else +#define FORCE_INLINE +#endif + +static inline FORCE_INLINE uint32_t rotl32 ( uint32_t x, int8_t r ) +{ + return (x << r) | (x >> (32 - r)); +} + +static inline FORCE_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) + +//----------------------------------------------------------------------------- +// Block read - if your platform needs to do endian-swapping or can only +// handle aligned reads, do the conversion here + +#define getblock(p, i) (p[i]) + +//----------------------------------------------------------------------------- +// Finalization mix - force all bits of a hash block to avalanche + +static inline FORCE_INLINE uint32_t fmix32 ( uint32_t h ) +{ + h ^= h >> 16; + h *= 0x85ebca6b; + h ^= h >> 13; + h *= 0xc2b2ae35; + h ^= h >> 16; + + return h; +} + +//---------- + +static inline FORCE_INLINE uint64_t fmix64 ( 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; + int i; + + uint32_t h1 = seed; + + uint32_t c1 = 0xcc9e2d51; + uint32_t c2 = 0x1b873593; + + //---------- + // body + + const uint32_t * blocks = (const uint32_t *)(data + nblocks*4); + + for(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(k1,15); k1 *= c2; h1 ^= k1; + }; + + //---------- + // finalization + + h1 ^= len; + + h1 = fmix32(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; + int i; + + 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(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 = fmix32(h1); + h2 = fmix32(h2); + h3 = fmix32(h3); + h4 = fmix32(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; + int i; + + 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(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 = fmix64(h1); + h2 = fmix64(h2); + + h1 += h2; + h2 += h1; + + ((uint64_t*)out)[0] = h1; + ((uint64_t*)out)[1] = h2; +} + +//----------------------------------------------------------------------------- + diff --git a/src/Data/Dish/Murmur3.hs b/src/Data/Dish/Murmur3.hs new file mode 100644 --- /dev/null +++ b/src/Data/Dish/Murmur3.hs @@ -0,0 +1,150 @@ +{-# LANGUAGE ForeignFunctionInterface #-} +{- | +This is a Haskell wrapper around the C port of MurmurHash3. + +MurmurHash3 is available at + +The hash functions are designed to work efficiently on x86 processors; +in particular, they make some assumptions about the endianness of the processor, +and about the speed of unaligned reads. +-} +module Data.Dish.Murmur3( + -- * Default/Direct Map + -- $default + murmur3, + -- * X86 32 bits + -- $32 + murmur3Int, + -- * X86 128 bits + -- $x128 + murmur3IntegerX86, + -- * X64 128 bits + -- $64_128 + murmur3IntegerX64, + -- * FFI + murmur3Raw, + -- * Unsafe + unsafeMurmur3Int, + unsafeMurmur3IntegerX86, + unsafeMurmur3IntegerX64, + -- * Murmur3 Hash Version + MHV(..) + ) where +import Foreign.C +import Foreign.Ptr +import Foreign +import qualified Data.List as L +import qualified Data.Bits as B +import qualified System.IO.Unsafe as US + +-- Murmur Hash version, one of +data MHV = X86_32 | X86_128 | X64_128 + + +{-$default +Simple, verbose interface for generating hashes +-} +-- | Base function, which allows you to choose which 'MHV' to use +murmur3 :: String -- ^ The string to be hashed + -> Int -- ^ A seed value for the hash function + -> MHV -- ^ Which Murmur Hash version to use 'X86_32', 'X86_128' or 'X64_128' + -> IO [Int] -- ^ returns 4, 32 bit ints, if 'X86_32' is used only the first has a value and the other 3 are 0 +murmur3 v s ver = do m <- murmur3Raw v s ver; toArr m + where + toArr :: [CUInt] -> IO [Int] + toArr [] = return [] + toArr l = return $ b l [] + where b :: [CUInt] -> [Int] -> [Int] + b xs l2 = foldl (\ list x -> list ++ [w x] ) l2 xs + w :: CUInt -> Int + w = fromIntegral + +{-$32 +Generate 32 bit hash values +-} +{- | has the lowest throughput, but also the lowest latency. If you're making a +hash table that usually has small keys, this is probably the one you want to use +on 32-bit machines. It has a 32-bit output. -} +murmur3Int :: String -- ^ The string to be hashed + -> Int -- ^ A seed value for the hash function + -> IO Int -- ^ 32 bit number generated from the string +murmur3Int val seed = do v <- murmur3Raw val seed X86_32; + -- safe to use L.head, list is never empty even if all vals are 0 + return $ fromIntegral (L.head v) + +{-$x128 +Generate 128 bit hash values, optimized for 32 bit systems +-} +{- | Generate a 128 bit hash from the given value, this function's implementation + is optimized for 32 bit architectures but works on any. + Has about 30% higher throughput than 'murmur3Int'. Be warned, though, + that its latency for a single 16-byte key is about 86% longer! +-} +murmur3IntegerX86 :: String -- ^ The string to be hashed + -> Int -- ^ A seed value for the hash function + -> IO Integer -- ^ 128 bit number generated from the string +murmur3IntegerX86 val seed = x128 val seed X86_128 + +{-$64_128 +Generate 128 bit hash values, optimized for 64 bit systems +-} +{- | Generate a 128 bit hash from the given value, this function's implementation + is optimized for x64 architectures but works on any. + Its throughput is 250% higher than 'murmur3IntegerX86', but it has roughly + the same latency. +-} +murmur3IntegerX64 :: String -- ^ The string to be hashed + -> Int -- ^ A seed value for the hash function + -> IO Integer -- ^ 128 bit number generated from the string +murmur3IntegerX64 val seed = x128 val seed X64_128 + +foreign import ccall "MurmurHash3_x86_32" c_x86_32 + :: CString -> CInt -> CUInt -> Ptr CUInt -> IO () + +foreign import ccall "MurmurHash3_x86_128" c_x86_128 + :: CString -> CInt -> CUInt -> Ptr CUInt -> IO () + +foreign import ccall "MurmurHash3_x64_128" c_x64_128 + :: CString -> CInt -> CUInt -> Ptr CUInt -> IO () + +-- | all murmur functions use this and manipulate its response to return a different format +murmur3Raw :: String -> Int -> MHV -> IO [CUInt] +murmur3Raw val seed ver = do + val' <- withCAStringLen val $ \x -> return x + let cstr = strFromCStr val' + let strLength = strLFromCStr val' + outPtr <- mallocArray arrSize + doHash ver cstr strLength (fromIntegral seed) outPtr + peekArray arrSize outPtr + where arrSize = 4 + strFromCStr :: CStringLen -> CString + strFromCStr = fst + strLFromCStr :: CStringLen -> CInt + strLFromCStr i = fromIntegral $ snd i + --version value size seed out + doHash :: MHV -> CString -> CInt -> CUInt -> Ptr CUInt -> IO() + doHash X86_32 v s se o = c_x86_32 v s se o + doHash X86_128 v s se o = c_x86_128 v s se o + doHash X64_128 v s se o = c_x64_128 v s se o + +unsafeMurmur3Int :: String -> Int -> Int +unsafeMurmur3Int val seed = US.unsafePerformIO $ murmur3Int val seed + +unsafeMurmur3IntegerX86 :: String -> Int -> Integer +unsafeMurmur3IntegerX86 val seed = US.unsafePerformIO $ murmur3IntegerX86 val seed + +unsafeMurmur3IntegerX64 :: String -> Int -> Integer +unsafeMurmur3IntegerX64 val seed = US.unsafePerformIO $ murmur3IntegerX64 val seed + +x128 :: String -> Int -> MHV -> IO Integer +x128 val seed ver= do + v <- hash ver + return $ twiddle 0 v + where hash :: MHV -> IO [CUInt] + hash X86_128 = murmur3Raw val seed X86_128 + hash X64_128 = murmur3Raw val seed X64_128 + hash _ = return [] + twiddle :: Integer -> [CUInt] -> Integer + twiddle i [] = i + twiddle i (0:xs) = twiddle i xs -- don't shift when val is 0 + twiddle i (x:xs) = twiddle (B.shift i (B.bitSize x) `B.xor` fromIntegral x) xs