From fdae7d486b037ae45b298344ed327ca4439299c2 Mon Sep 17 00:00:00 2001 From: lumina37 Date: Mon, 30 Dec 2024 12:56:47 +0800 Subject: [PATCH] chore: bump bundled xxhash to v0.8.3 --- .../helper/crypto/include/xxHash/xxhash.h | 549 +++++++++++------- 1 file changed, 348 insertions(+), 201 deletions(-) diff --git a/aiotieba/helper/crypto/include/xxHash/xxhash.h b/aiotieba/helper/crypto/include/xxHash/xxhash.h index c2344b8d..2e85ac6e 100644 --- a/aiotieba/helper/crypto/include/xxHash/xxhash.h +++ b/aiotieba/helper/crypto/include/xxHash/xxhash.h @@ -1110,6 +1110,23 @@ XXH_PUBLIC_API XXH_PUREF XXH64_hash_t XXH64_hashFromCanonical(XXH_NOESCAPE const * * The API supports one-shot hashing, streaming mode, and custom secrets. */ + +/*! + * @ingroup tuning + * @brief Possible values for @ref XXH_VECTOR. + * + * Unless set explicitly, determined automatically. + */ +# define XXH_SCALAR 0 /*!< Portable scalar version */ +# define XXH_SSE2 1 /*!< SSE2 for Pentium 4, Opteron, all x86_64. */ +# define XXH_AVX2 2 /*!< AVX2 for Haswell and Bulldozer */ +# define XXH_AVX512 3 /*!< AVX512 for Skylake and Icelake */ +# define XXH_NEON 4 /*!< NEON for most ARMv7-A, all AArch64, and WASM SIMD128 */ +# define XXH_VSX 5 /*!< VSX and ZVector for POWER8/z13 (64-bit) */ +# define XXH_SVE 6 /*!< SVE for some ARMv8-A and ARMv9-A */ +# define XXH_LSX 7 /*!< LSX (128-bit SIMD) for LoongArch64 */ + + /*-********************************************************************** * XXH3 64-bit variant ************************************************************************/ @@ -1655,9 +1672,9 @@ XXH_PUBLIC_API XXH_PUREF XXH128_hash_t XXH128_hashFromCanonical(XXH_NOESCAPE con struct XXH32_state_s { XXH32_hash_t total_len_32; /*!< Total length hashed, modulo 2^32 */ XXH32_hash_t large_len; /*!< Whether the hash is >= 16 (handles @ref total_len_32 overflow) */ - XXH32_hash_t v[4]; /*!< Accumulator lanes */ - XXH32_hash_t mem32[4]; /*!< Internal buffer for partial reads. Treated as unsigned char[16]. */ - XXH32_hash_t memsize; /*!< Amount of data in @ref mem32 */ + XXH32_hash_t acc[4]; /*!< Accumulator lanes */ + unsigned char buffer[16]; /*!< Internal buffer for partial reads. */ + XXH32_hash_t bufferedSize; /*!< Amount of data in @ref buffer */ XXH32_hash_t reserved; /*!< Reserved field. Do not read nor write to it. */ }; /* typedef'd to XXH32_state_t */ @@ -1678,9 +1695,9 @@ struct XXH32_state_s { */ struct XXH64_state_s { XXH64_hash_t total_len; /*!< Total length hashed. This is always 64-bit. */ - XXH64_hash_t v[4]; /*!< Accumulator lanes */ - XXH64_hash_t mem64[4]; /*!< Internal buffer for partial reads. Treated as unsigned char[32]. */ - XXH32_hash_t memsize; /*!< Amount of data in @ref mem64 */ + XXH64_hash_t acc[4]; /*!< Accumulator lanes */ + unsigned char buffer[32]; /*!< Internal buffer for partial reads.. */ + XXH32_hash_t bufferedSize; /*!< Amount of data in @ref buffer */ XXH32_hash_t reserved32; /*!< Reserved field, needed for padding anyways*/ XXH64_hash_t reserved64; /*!< Reserved field. Do not read or write to it. */ }; /* typedef'd to XXH64_state_t */ @@ -2418,12 +2435,34 @@ static void* XXH_memcpy(void* dest, const void* src, size_t size) # define XXH_NO_INLINE static #endif +#if defined(XXH_INLINE_ALL) +# define XXH_STATIC XXH_FORCE_INLINE +#else +# define XXH_STATIC static +#endif + #if XXH3_INLINE_SECRET # define XXH3_WITH_SECRET_INLINE XXH_FORCE_INLINE #else # define XXH3_WITH_SECRET_INLINE XXH_NO_INLINE #endif +#if ((defined(sun) || defined(__sun)) && __cplusplus) /* Solaris includes __STDC_VERSION__ with C++. Tested with GCC 5.5 */ +# define XXH_RESTRICT /* disable */ +#elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* >= C99 */ +# define XXH_RESTRICT restrict +#elif (defined (__GNUC__) && ((__GNUC__ > 3) || (__GNUC__ == 3 && __GNUC_MINOR__ >= 1))) \ + || (defined (__clang__)) \ + || (defined (_MSC_VER) && (_MSC_VER >= 1400)) \ + || (defined (__INTEL_COMPILER) && (__INTEL_COMPILER >= 1300)) +/* + * There are a LOT more compilers that recognize __restrict but this + * covers the major ones. + */ +# define XXH_RESTRICT __restrict +#else +# define XXH_RESTRICT /* disable */ +#endif /* ************************************* * Debug @@ -2955,6 +2994,61 @@ static xxh_u32 XXH32_avalanche(xxh_u32 hash) #define XXH_get32bits(p) XXH_readLE32_align(p, align) +/*! + * @internal + * @brief Sets up the initial accumulator state for XXH32(). + */ +XXH_FORCE_INLINE void +XXH32_initAccs(xxh_u32 *acc, xxh_u32 seed) +{ + XXH_ASSERT(acc != NULL); + acc[0] = seed + XXH_PRIME32_1 + XXH_PRIME32_2; + acc[1] = seed + XXH_PRIME32_2; + acc[2] = seed + 0; + acc[3] = seed - XXH_PRIME32_1; +} + +/*! + * @internal + * @brief Consumes a block of data for XXH32(). + * + * @return the end input pointer. + */ +XXH_FORCE_INLINE const xxh_u8 * +XXH32_consumeLong( + xxh_u32 *XXH_RESTRICT acc, + xxh_u8 const *XXH_RESTRICT input, + size_t len, + XXH_alignment align +) +{ + const xxh_u8* const bEnd = input + len; + const xxh_u8* const limit = bEnd - 15; + XXH_ASSERT(acc != NULL); + XXH_ASSERT(input != NULL); + XXH_ASSERT(len >= 16); + do { + acc[0] = XXH32_round(acc[0], XXH_get32bits(input)); input += 4; + acc[1] = XXH32_round(acc[1], XXH_get32bits(input)); input += 4; + acc[2] = XXH32_round(acc[2], XXH_get32bits(input)); input += 4; + acc[3] = XXH32_round(acc[3], XXH_get32bits(input)); input += 4; + } while (input < limit); + + return input; +} + +/*! + * @internal + * @brief Merges the accumulator lanes together for XXH32() + */ +XXH_FORCE_INLINE XXH_PUREF xxh_u32 +XXH32_mergeAccs(const xxh_u32 *acc) +{ + XXH_ASSERT(acc != NULL); + return XXH_rotl32(acc[0], 1) + XXH_rotl32(acc[1], 7) + + XXH_rotl32(acc[2], 12) + XXH_rotl32(acc[3], 18); +} + /*! * @internal * @brief Processes the last 0-15 bytes of @p ptr. @@ -3067,22 +3161,12 @@ XXH32_endian_align(const xxh_u8* input, size_t len, xxh_u32 seed, XXH_alignment if (input==NULL) XXH_ASSERT(len == 0); if (len>=16) { - const xxh_u8* const bEnd = input + len; - const xxh_u8* const limit = bEnd - 15; - xxh_u32 v1 = seed + XXH_PRIME32_1 + XXH_PRIME32_2; - xxh_u32 v2 = seed + XXH_PRIME32_2; - xxh_u32 v3 = seed + 0; - xxh_u32 v4 = seed - XXH_PRIME32_1; + xxh_u32 acc[4]; + XXH32_initAccs(acc, seed); - do { - v1 = XXH32_round(v1, XXH_get32bits(input)); input += 4; - v2 = XXH32_round(v2, XXH_get32bits(input)); input += 4; - v3 = XXH32_round(v3, XXH_get32bits(input)); input += 4; - v4 = XXH32_round(v4, XXH_get32bits(input)); input += 4; - } while (input < limit); - - h32 = XXH_rotl32(v1, 1) + XXH_rotl32(v2, 7) - + XXH_rotl32(v3, 12) + XXH_rotl32(v4, 18); + input = XXH32_consumeLong(acc, input, len, align); + + h32 = XXH32_mergeAccs(acc); } else { h32 = seed + XXH_PRIME32_5; } @@ -3138,10 +3222,7 @@ XXH_PUBLIC_API XXH_errorcode XXH32_reset(XXH32_state_t* statePtr, XXH32_hash_t s { XXH_ASSERT(statePtr != NULL); memset(statePtr, 0, sizeof(*statePtr)); - statePtr->v[0] = seed + XXH_PRIME32_1 + XXH_PRIME32_2; - statePtr->v[1] = seed + XXH_PRIME32_2; - statePtr->v[2] = seed + 0; - statePtr->v[3] = seed - XXH_PRIME32_1; + XXH32_initAccs(statePtr->acc, seed); return XXH_OK; } @@ -3155,45 +3236,37 @@ XXH32_update(XXH32_state_t* state, const void* input, size_t len) return XXH_OK; } - { const xxh_u8* p = (const xxh_u8*)input; - const xxh_u8* const bEnd = p + len; + state->total_len_32 += (XXH32_hash_t)len; + state->large_len |= (XXH32_hash_t)((len>=16) | (state->total_len_32>=16)); - state->total_len_32 += (XXH32_hash_t)len; - state->large_len |= (XXH32_hash_t)((len>=16) | (state->total_len_32>=16)); + XXH_ASSERT(state->bufferedSize < sizeof(state->buffer)); + if (len < sizeof(state->buffer) - state->bufferedSize) { /* fill in tmp buffer */ + XXH_memcpy(state->buffer + state->bufferedSize, input, len); + state->bufferedSize += (XXH32_hash_t)len; + return XXH_OK; + } - if (state->memsize + len < 16) { /* fill in tmp buffer */ - XXH_memcpy((xxh_u8*)(state->mem32) + state->memsize, input, len); - state->memsize += (XXH32_hash_t)len; - return XXH_OK; - } + { const xxh_u8* xinput = (const xxh_u8*)input; + const xxh_u8* const bEnd = xinput + len; - if (state->memsize) { /* some data left from previous update */ - XXH_memcpy((xxh_u8*)(state->mem32) + state->memsize, input, 16-state->memsize); - { const xxh_u32* p32 = state->mem32; - state->v[0] = XXH32_round(state->v[0], XXH_readLE32(p32)); p32++; - state->v[1] = XXH32_round(state->v[1], XXH_readLE32(p32)); p32++; - state->v[2] = XXH32_round(state->v[2], XXH_readLE32(p32)); p32++; - state->v[3] = XXH32_round(state->v[3], XXH_readLE32(p32)); - } - p += 16-state->memsize; - state->memsize = 0; + if (state->bufferedSize) { /* non-empty buffer: complete first */ + XXH_memcpy(state->buffer + state->bufferedSize, xinput, sizeof(state->buffer) - state->bufferedSize); + xinput += sizeof(state->buffer) - state->bufferedSize; + /* then process one round */ + (void)XXH32_consumeLong(state->acc, state->buffer, sizeof(state->buffer), XXH_aligned); + state->bufferedSize = 0; } - if (p <= bEnd-16) { - const xxh_u8* const limit = bEnd - 16; - - do { - state->v[0] = XXH32_round(state->v[0], XXH_readLE32(p)); p+=4; - state->v[1] = XXH32_round(state->v[1], XXH_readLE32(p)); p+=4; - state->v[2] = XXH32_round(state->v[2], XXH_readLE32(p)); p+=4; - state->v[3] = XXH32_round(state->v[3], XXH_readLE32(p)); p+=4; - } while (p<=limit); - + XXH_ASSERT(xinput <= bEnd); + if ((size_t)(bEnd - xinput) >= sizeof(state->buffer)) { + /* Process the remaining data */ + xinput = XXH32_consumeLong(state->acc, xinput, (size_t)(bEnd - xinput), XXH_unaligned); } - if (p < bEnd) { - XXH_memcpy(state->mem32, p, (size_t)(bEnd-p)); - state->memsize = (unsigned)(bEnd-p); + if (xinput < bEnd) { + /* Copy the leftover to the tmp buffer */ + XXH_memcpy(state->buffer, xinput, (size_t)(bEnd-xinput)); + state->bufferedSize = (unsigned)(bEnd-xinput); } } @@ -3207,17 +3280,14 @@ XXH_PUBLIC_API XXH32_hash_t XXH32_digest(const XXH32_state_t* state) xxh_u32 h32; if (state->large_len) { - h32 = XXH_rotl32(state->v[0], 1) - + XXH_rotl32(state->v[1], 7) - + XXH_rotl32(state->v[2], 12) - + XXH_rotl32(state->v[3], 18); + h32 = XXH32_mergeAccs(state->acc); } else { - h32 = state->v[2] /* == seed */ + XXH_PRIME32_5; + h32 = state->acc[2] /* == seed */ + XXH_PRIME32_5; } h32 += state->total_len_32; - return XXH32_finalize(h32, (const xxh_u8*)state->mem32, state->memsize, XXH_aligned); + return XXH32_finalize(h32, state->buffer, state->bufferedSize, XXH_aligned); } #endif /* !XXH_NO_STREAM */ @@ -3443,6 +3513,85 @@ static xxh_u64 XXH64_avalanche(xxh_u64 hash) #define XXH_get64bits(p) XXH_readLE64_align(p, align) +/*! + * @internal + * @brief Sets up the initial accumulator state for XXH64(). + */ +XXH_FORCE_INLINE void +XXH64_initAccs(xxh_u64 *acc, xxh_u64 seed) +{ + XXH_ASSERT(acc != NULL); + acc[0] = seed + XXH_PRIME64_1 + XXH_PRIME64_2; + acc[1] = seed + XXH_PRIME64_2; + acc[2] = seed + 0; + acc[3] = seed - XXH_PRIME64_1; +} + +/*! + * @internal + * @brief Consumes a block of data for XXH64(). + * + * @return the end input pointer. + */ +XXH_FORCE_INLINE const xxh_u8 * +XXH64_consumeLong( + xxh_u64 *XXH_RESTRICT acc, + xxh_u8 const *XXH_RESTRICT input, + size_t len, + XXH_alignment align +) +{ + const xxh_u8* const bEnd = input + len; + const xxh_u8* const limit = bEnd - 31; + XXH_ASSERT(acc != NULL); + XXH_ASSERT(input != NULL); + XXH_ASSERT(len >= 32); + do { + /* reroll on 32-bit */ + if (sizeof(void *) < sizeof(xxh_u64)) { + size_t i; + for (i = 0; i < 4; i++) { + acc[i] = XXH64_round(acc[i], XXH_get64bits(input)); + input += 8; + } + } else { + acc[0] = XXH64_round(acc[0], XXH_get64bits(input)); input += 8; + acc[1] = XXH64_round(acc[1], XXH_get64bits(input)); input += 8; + acc[2] = XXH64_round(acc[2], XXH_get64bits(input)); input += 8; + acc[3] = XXH64_round(acc[3], XXH_get64bits(input)); input += 8; + } + } while (input < limit); + + return input; +} + +/*! + * @internal + * @brief Merges the accumulator lanes together for XXH64() + */ +XXH_FORCE_INLINE XXH_PUREF xxh_u64 +XXH64_mergeAccs(const xxh_u64 *acc) +{ + XXH_ASSERT(acc != NULL); + { + xxh_u64 h64 = XXH_rotl64(acc[0], 1) + XXH_rotl64(acc[1], 7) + + XXH_rotl64(acc[2], 12) + XXH_rotl64(acc[3], 18); + /* reroll on 32-bit */ + if (sizeof(void *) < sizeof(xxh_u64)) { + size_t i; + for (i = 0; i < 4; i++) { + h64 = XXH64_mergeRound(h64, acc[i]); + } + } else { + h64 = XXH64_mergeRound(h64, acc[0]); + h64 = XXH64_mergeRound(h64, acc[1]); + h64 = XXH64_mergeRound(h64, acc[2]); + h64 = XXH64_mergeRound(h64, acc[3]); + } + return h64; + } +} + /*! * @internal * @brief Processes the last 0-31 bytes of @p ptr. @@ -3458,7 +3607,7 @@ static xxh_u64 XXH64_avalanche(xxh_u64 hash) * @return The finalized hash * @see XXH32_finalize(). */ -static XXH_PUREF xxh_u64 +XXH_STATIC XXH_PUREF xxh_u64 XXH64_finalize(xxh_u64 hash, const xxh_u8* ptr, size_t len, XXH_alignment align) { if (ptr==NULL) XXH_ASSERT(len == 0); @@ -3508,27 +3657,13 @@ XXH64_endian_align(const xxh_u8* input, size_t len, xxh_u64 seed, XXH_alignment xxh_u64 h64; if (input==NULL) XXH_ASSERT(len == 0); - if (len>=32) { - const xxh_u8* const bEnd = input + len; - const xxh_u8* const limit = bEnd - 31; - xxh_u64 v1 = seed + XXH_PRIME64_1 + XXH_PRIME64_2; - xxh_u64 v2 = seed + XXH_PRIME64_2; - xxh_u64 v3 = seed + 0; - xxh_u64 v4 = seed - XXH_PRIME64_1; + if (len>=32) { /* Process a large block of data */ + xxh_u64 acc[4]; + XXH64_initAccs(acc, seed); - do { - v1 = XXH64_round(v1, XXH_get64bits(input)); input+=8; - v2 = XXH64_round(v2, XXH_get64bits(input)); input+=8; - v3 = XXH64_round(v3, XXH_get64bits(input)); input+=8; - v4 = XXH64_round(v4, XXH_get64bits(input)); input+=8; - } while (inputv[0] = seed + XXH_PRIME64_1 + XXH_PRIME64_2; - statePtr->v[1] = seed + XXH_PRIME64_2; - statePtr->v[2] = seed + 0; - statePtr->v[3] = seed - XXH_PRIME64_1; + XXH64_initAccs(statePtr->acc, seed); return XXH_OK; } @@ -3600,42 +3732,36 @@ XXH64_update (XXH_NOESCAPE XXH64_state_t* state, XXH_NOESCAPE const void* input, return XXH_OK; } - { const xxh_u8* p = (const xxh_u8*)input; - const xxh_u8* const bEnd = p + len; + state->total_len += len; - state->total_len += len; + XXH_ASSERT(state->bufferedSize <= sizeof(state->buffer)); + if (len < sizeof(state->buffer) - state->bufferedSize) { /* fill in tmp buffer */ + XXH_memcpy(state->buffer + state->bufferedSize, input, len); + state->bufferedSize += (XXH32_hash_t)len; + return XXH_OK; + } - if (state->memsize + len < 32) { /* fill in tmp buffer */ - XXH_memcpy(((xxh_u8*)state->mem64) + state->memsize, input, len); - state->memsize += (xxh_u32)len; - return XXH_OK; - } + { const xxh_u8* xinput = (const xxh_u8*)input; + const xxh_u8* const bEnd = xinput + len; - if (state->memsize) { /* tmp buffer is full */ - XXH_memcpy(((xxh_u8*)state->mem64) + state->memsize, input, 32-state->memsize); - state->v[0] = XXH64_round(state->v[0], XXH_readLE64(state->mem64+0)); - state->v[1] = XXH64_round(state->v[1], XXH_readLE64(state->mem64+1)); - state->v[2] = XXH64_round(state->v[2], XXH_readLE64(state->mem64+2)); - state->v[3] = XXH64_round(state->v[3], XXH_readLE64(state->mem64+3)); - p += 32 - state->memsize; - state->memsize = 0; + if (state->bufferedSize) { /* non-empty buffer => complete first */ + XXH_memcpy(state->buffer + state->bufferedSize, xinput, sizeof(state->buffer) - state->bufferedSize); + xinput += sizeof(state->buffer) - state->bufferedSize; + /* and process one round */ + (void)XXH64_consumeLong(state->acc, state->buffer, sizeof(state->buffer), XXH_aligned); + state->bufferedSize = 0; } - if (p+32 <= bEnd) { - const xxh_u8* const limit = bEnd - 32; - - do { - state->v[0] = XXH64_round(state->v[0], XXH_readLE64(p)); p+=8; - state->v[1] = XXH64_round(state->v[1], XXH_readLE64(p)); p+=8; - state->v[2] = XXH64_round(state->v[2], XXH_readLE64(p)); p+=8; - state->v[3] = XXH64_round(state->v[3], XXH_readLE64(p)); p+=8; - } while (p<=limit); - + XXH_ASSERT(xinput <= bEnd); + if ((size_t)(bEnd - xinput) >= sizeof(state->buffer)) { + /* Process the remaining data */ + xinput = XXH64_consumeLong(state->acc, xinput, (size_t)(bEnd - xinput), XXH_unaligned); } - if (p < bEnd) { - XXH_memcpy(state->mem64, p, (size_t)(bEnd-p)); - state->memsize = (unsigned)(bEnd-p); + if (xinput < bEnd) { + /* Copy the leftover to the tmp buffer */ + XXH_memcpy(state->buffer, xinput, (size_t)(bEnd-xinput)); + state->bufferedSize = (unsigned)(bEnd-xinput); } } @@ -3649,18 +3775,14 @@ XXH_PUBLIC_API XXH64_hash_t XXH64_digest(XXH_NOESCAPE const XXH64_state_t* state xxh_u64 h64; if (state->total_len >= 32) { - h64 = XXH_rotl64(state->v[0], 1) + XXH_rotl64(state->v[1], 7) + XXH_rotl64(state->v[2], 12) + XXH_rotl64(state->v[3], 18); - h64 = XXH64_mergeRound(h64, state->v[0]); - h64 = XXH64_mergeRound(h64, state->v[1]); - h64 = XXH64_mergeRound(h64, state->v[2]); - h64 = XXH64_mergeRound(h64, state->v[3]); + h64 = XXH64_mergeAccs(state->acc); } else { - h64 = state->v[2] /*seed*/ + XXH_PRIME64_5; + h64 = state->acc[2] /*seed*/ + XXH_PRIME64_5; } h64 += (xxh_u64) state->total_len; - return XXH64_finalize(h64, (const xxh_u8*)state->mem64, (size_t)state->total_len, XXH_aligned); + return XXH64_finalize(h64, state->buffer, (size_t)state->total_len, XXH_aligned); } #endif /* !XXH_NO_STREAM */ @@ -3695,22 +3817,6 @@ XXH_PUBLIC_API XXH64_hash_t XXH64_hashFromCanonical(XXH_NOESCAPE const XXH64_can /* === Compiler specifics === */ -#if ((defined(sun) || defined(__sun)) && __cplusplus) /* Solaris includes __STDC_VERSION__ with C++. Tested with GCC 5.5 */ -# define XXH_RESTRICT /* disable */ -#elif defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* >= C99 */ -# define XXH_RESTRICT restrict -#elif (defined (__GNUC__) && ((__GNUC__ > 3) || (__GNUC__ == 3 && __GNUC_MINOR__ >= 1))) \ - || (defined (__clang__)) \ - || (defined (_MSC_VER) && (_MSC_VER >= 1400)) \ - || (defined (__INTEL_COMPILER) && (__INTEL_COMPILER >= 1300)) -/* - * There are a LOT more compilers that recognize __restrict but this - * covers the major ones. - */ -# define XXH_RESTRICT __restrict -#else -# define XXH_RESTRICT /* disable */ -#endif #if (defined(__GNUC__) && (__GNUC__ >= 3)) \ || (defined(__INTEL_COMPILER) && (__INTEL_COMPILER >= 800)) \ @@ -3749,6 +3855,8 @@ XXH_PUBLIC_API XXH64_hash_t XXH64_hashFromCanonical(XXH_NOESCAPE const XXH64_can # include # elif defined(__SSE2__) # include +# elif defined(__loongarch_sx) +# include # endif #endif @@ -3845,33 +3953,6 @@ XXH_PUBLIC_API XXH64_hash_t XXH64_hashFromCanonical(XXH_NOESCAPE const XXH64_can * implementation. */ # define XXH_VECTOR XXH_SCALAR -/*! - * @ingroup tuning - * @brief Possible values for @ref XXH_VECTOR. - * - * Note that these are actually implemented as macros. - * - * If this is not defined, it is detected automatically. - * internal macro XXH_X86DISPATCH overrides this. - */ -enum XXH_VECTOR_TYPE /* fake enum */ { - XXH_SCALAR = 0, /*!< Portable scalar version */ - XXH_SSE2 = 1, /*!< - * SSE2 for Pentium 4, Opteron, all x86_64. - * - * @note SSE2 is also guaranteed on Windows 10, macOS, and - * Android x86. - */ - XXH_AVX2 = 2, /*!< AVX2 for Haswell and Bulldozer */ - XXH_AVX512 = 3, /*!< AVX512 for Skylake and Icelake */ - XXH_NEON = 4, /*!< - * NEON for most ARMv7-A, all AArch64, and WASM SIMD128 - * via the SIMDeverywhere polyfill provided with the - * Emscripten SDK. - */ - XXH_VSX = 5, /*!< VSX and ZVector for POWER8/z13 (64-bit) */ - XXH_SVE = 6, /*!< SVE for some ARMv8-A and ARMv9-A */ -}; /*! * @ingroup tuning * @brief Selects the minimum alignment for XXH3's accumulators. @@ -3886,13 +3967,6 @@ enum XXH_VECTOR_TYPE /* fake enum */ { /* Actual definition */ #ifndef XXH_DOXYGEN -# define XXH_SCALAR 0 -# define XXH_SSE2 1 -# define XXH_AVX2 2 -# define XXH_AVX512 3 -# define XXH_NEON 4 -# define XXH_VSX 5 -# define XXH_SVE 6 #endif #ifndef XXH_VECTOR /* can be defined on command line */ @@ -3917,6 +3991,8 @@ enum XXH_VECTOR_TYPE /* fake enum */ { || (defined(__s390x__) && defined(__VEC__)) \ && defined(__GNUC__) /* TODO: IBM XL */ # define XXH_VECTOR XXH_VSX +# elif defined(__loongarch_sx) +# define XXH_VECTOR XXH_LSX # else # define XXH_VECTOR XXH_SCALAR # endif @@ -3954,6 +4030,8 @@ enum XXH_VECTOR_TYPE /* fake enum */ { # define XXH_ACC_ALIGN 64 # elif XXH_VECTOR == XXH_SVE /* sve */ # define XXH_ACC_ALIGN 64 +# elif XXH_VECTOR == XXH_LSX /* lsx */ +# define XXH_ACC_ALIGN 64 # endif #endif @@ -5591,6 +5669,71 @@ XXH3_accumulate_sve(xxh_u64* XXH_RESTRICT acc, #endif +#if (XXH_VECTOR == XXH_LSX) +#define _LSX_SHUFFLE(z, y, x, w) (((z) << 6) | ((y) << 4) | ((x) << 2) | (w)) + +XXH_FORCE_INLINE void +XXH3_accumulate_512_lsx( void* XXH_RESTRICT acc, + const void* XXH_RESTRICT input, + const void* XXH_RESTRICT secret) +{ + XXH_ASSERT((((size_t)acc) & 15) == 0); + { + __m128i* const xacc = (__m128i *) acc; + const __m128i* const xinput = (const __m128i *) input; + const __m128i* const xsecret = (const __m128i *) secret; + + for (size_t i = 0; i < XXH_STRIPE_LEN / sizeof(__m128i); i++) { + /* data_vec = xinput[i]; */ + __m128i const data_vec = __lsx_vld(xinput + i, 0); + /* key_vec = xsecret[i]; */ + __m128i const key_vec = __lsx_vld(xsecret + i, 0); + /* data_key = data_vec ^ key_vec; */ + __m128i const data_key = __lsx_vxor_v(data_vec, key_vec); + /* data_key_lo = data_key >> 32; */ + __m128i const data_key_lo = __lsx_vsrli_d(data_key, 32); + // __m128i const data_key_lo = __lsx_vsrli_d(data_key, 32); + /* product = (data_key & 0xffffffff) * (data_key_lo & 0xffffffff); */ + __m128i const product = __lsx_vmulwev_d_wu(data_key, data_key_lo); + /* xacc[i] += swap(data_vec); */ + __m128i const data_swap = __lsx_vshuf4i_w(data_vec, _LSX_SHUFFLE(1, 0, 3, 2)); + __m128i const sum = __lsx_vadd_d(xacc[i], data_swap); + /* xacc[i] += product; */ + xacc[i] = __lsx_vadd_d(product, sum); + } + } +} +XXH_FORCE_INLINE XXH3_ACCUMULATE_TEMPLATE(lsx) + +XXH_FORCE_INLINE void +XXH3_scrambleAcc_lsx(void* XXH_RESTRICT acc, const void* XXH_RESTRICT secret) +{ + XXH_ASSERT((((size_t)acc) & 15) == 0); + { + __m128i* const xacc = (__m128i*) acc; + const __m128i* const xsecret = (const __m128i *) secret; + const __m128i prime32 = __lsx_vreplgr2vr_w((int)XXH_PRIME32_1); + + for (size_t i = 0; i < XXH_STRIPE_LEN / sizeof(__m128i); i++) { + /* xacc[i] ^= (xacc[i] >> 47) */ + __m128i const acc_vec = xacc[i]; + __m128i const shifted = __lsx_vsrli_d(acc_vec, 47); + __m128i const data_vec = __lsx_vxor_v(acc_vec, shifted); + /* xacc[i] ^= xsecret[i]; */ + __m128i const key_vec = __lsx_vld(xsecret + i, 0); + __m128i const data_key = __lsx_vxor_v(data_vec, key_vec); + + /* xacc[i] *= XXH_PRIME32_1; */ + __m128i const data_key_hi = __lsx_vsrli_d(data_key, 32); + __m128i const prod_lo = __lsx_vmulwev_d_wu(data_key, prime32); + __m128i const prod_hi = __lsx_vmulwev_d_wu(data_key_hi, prime32); + xacc[i] = __lsx_vadd_d(prod_lo, __lsx_vslli_d(prod_hi, 32)); + } + } +} + +#endif + /* scalar variants - universal */ #if defined(__aarch64__) && (defined(__GNUC__) || defined(__clang__)) @@ -5821,6 +5964,12 @@ typedef void (*XXH3_f_initCustomSecret)(void* XXH_RESTRICT, xxh_u64); #define XXH3_scrambleAcc XXH3_scrambleAcc_scalar #define XXH3_initCustomSecret XXH3_initCustomSecret_scalar +#elif (XXH_VECTOR == XXH_LSX) +#define XXH3_accumulate_512 XXH3_accumulate_512_lsx +#define XXH3_accumulate XXH3_accumulate_lsx +#define XXH3_scrambleAcc XXH3_scrambleAcc_lsx +#define XXH3_initCustomSecret XXH3_initCustomSecret_scalar + #else /* scalar */ #define XXH3_accumulate_512 XXH3_accumulate_512_scalar @@ -5876,7 +6025,7 @@ XXH3_mix2Accs(const xxh_u64* XXH_RESTRICT acc, const xxh_u8* XXH_RESTRICT secret acc[1] ^ XXH_readLE64(secret+8) ); } -static XXH64_hash_t +static XXH_PUREF XXH64_hash_t XXH3_mergeAccs(const xxh_u64* XXH_RESTRICT acc, const xxh_u8* XXH_RESTRICT secret, xxh_u64 start) { xxh_u64 result64 = start; @@ -5903,6 +6052,15 @@ XXH3_mergeAccs(const xxh_u64* XXH_RESTRICT acc, const xxh_u8* XXH_RESTRICT secre return XXH3_avalanche(result64); } +/* do not align on 8, so that the secret is different from the accumulator */ +#define XXH_SECRET_MERGEACCS_START 11 + +static XXH_PUREF XXH64_hash_t +XXH3_finalizeLong_64b(const xxh_u64* XXH_RESTRICT acc, const xxh_u8* XXH_RESTRICT secret, xxh_u64 len) +{ + return XXH3_mergeAccs(acc, secret + XXH_SECRET_MERGEACCS_START, len * XXH_PRIME64_1); +} + #define XXH3_INIT_ACC { XXH_PRIME32_3, XXH_PRIME64_1, XXH_PRIME64_2, XXH_PRIME64_3, \ XXH_PRIME64_4, XXH_PRIME32_2, XXH_PRIME64_5, XXH_PRIME32_1 } @@ -5918,10 +6076,8 @@ XXH3_hashLong_64b_internal(const void* XXH_RESTRICT input, size_t len, /* converge into final hash */ XXH_STATIC_ASSERT(sizeof(acc) == 64); - /* do not align on 8, so that the secret is different from the accumulator */ -#define XXH_SECRET_MERGEACCS_START 11 XXH_ASSERT(secretSize >= sizeof(acc) + XXH_SECRET_MERGEACCS_START); - return XXH3_mergeAccs(acc, (const xxh_u8*)secret + XXH_SECRET_MERGEACCS_START, (xxh_u64)len * XXH_PRIME64_1); + return XXH3_finalizeLong_64b(acc, (const xxh_u8*)secret, (xxh_u64)len); } /* @@ -6429,9 +6585,7 @@ XXH_PUBLIC_API XXH64_hash_t XXH3_64bits_digest (XXH_NOESCAPE const XXH3_state_t* if (state->totalLen > XXH3_MIDSIZE_MAX) { XXH_ALIGN(XXH_ACC_ALIGN) XXH64_hash_t acc[XXH_ACC_NB]; XXH3_digest_long(acc, state, secret); - return XXH3_mergeAccs(acc, - secret + XXH_SECRET_MERGEACCS_START, - (xxh_u64)state->totalLen * XXH_PRIME64_1); + return XXH3_finalizeLong_64b(acc, secret, (xxh_u64)state->totalLen); } /* totalLen <= XXH3_MIDSIZE_MAX: digesting a short input */ if (state->useSeed) @@ -6723,6 +6877,17 @@ XXH3_len_129to240_128b(const xxh_u8* XXH_RESTRICT input, size_t len, } } +static XXH_PUREF XXH128_hash_t +XXH3_finalizeLong_128b(const xxh_u64* XXH_RESTRICT acc, const xxh_u8* XXH_RESTRICT secret, size_t secretSize, xxh_u64 len) +{ + XXH128_hash_t h128; + h128.low64 = XXH3_finalizeLong_64b(acc, secret, len); + h128.high64 = XXH3_mergeAccs(acc, secret + secretSize + - XXH_STRIPE_LEN - XXH_SECRET_MERGEACCS_START, + ~(len * XXH_PRIME64_2)); + return h128; +} + XXH_FORCE_INLINE XXH128_hash_t XXH3_hashLong_128b_internal(const void* XXH_RESTRICT input, size_t len, const xxh_u8* XXH_RESTRICT secret, size_t secretSize, @@ -6736,16 +6901,7 @@ XXH3_hashLong_128b_internal(const void* XXH_RESTRICT input, size_t len, /* converge into final hash */ XXH_STATIC_ASSERT(sizeof(acc) == 64); XXH_ASSERT(secretSize >= sizeof(acc) + XXH_SECRET_MERGEACCS_START); - { XXH128_hash_t h128; - h128.low64 = XXH3_mergeAccs(acc, - secret + XXH_SECRET_MERGEACCS_START, - (xxh_u64)len * XXH_PRIME64_1); - h128.high64 = XXH3_mergeAccs(acc, - secret + secretSize - - sizeof(acc) - XXH_SECRET_MERGEACCS_START, - ~((xxh_u64)len * XXH_PRIME64_2)); - return h128; - } + return XXH3_finalizeLong_128b(acc, secret, secretSize, (xxh_u64)len); } /* @@ -6928,16 +7084,7 @@ XXH_PUBLIC_API XXH128_hash_t XXH3_128bits_digest (XXH_NOESCAPE const XXH3_state_ XXH_ALIGN(XXH_ACC_ALIGN) XXH64_hash_t acc[XXH_ACC_NB]; XXH3_digest_long(acc, state, secret); XXH_ASSERT(state->secretLimit + XXH_STRIPE_LEN >= sizeof(acc) + XXH_SECRET_MERGEACCS_START); - { XXH128_hash_t h128; - h128.low64 = XXH3_mergeAccs(acc, - secret + XXH_SECRET_MERGEACCS_START, - (xxh_u64)state->totalLen * XXH_PRIME64_1); - h128.high64 = XXH3_mergeAccs(acc, - secret + state->secretLimit + XXH_STRIPE_LEN - - sizeof(acc) - XXH_SECRET_MERGEACCS_START, - ~((xxh_u64)state->totalLen * XXH_PRIME64_2)); - return h128; - } + return XXH3_finalizeLong_128b(acc, secret, state->secretLimit + XXH_STRIPE_LEN, (xxh_u64)state->totalLen); } /* len <= XXH3_MIDSIZE_MAX : short code */ if (state->useSeed) @@ -7088,4 +7235,4 @@ XXH3_generateSecret_fromSeed(XXH_NOESCAPE void* secretBuffer, XXH64_hash_t seed) #if defined (__cplusplus) } /* extern "C" */ -#endif +#endif \ No newline at end of file