From mboxrd@z Thu Jan 1 00:00:00 1970 From: Yerden Zhumabekov Subject: Re: [PATCH v3 3/5] hash: add fallback to software CRC32 implementation Date: Tue, 18 Nov 2014 10:56:24 +0600 Message-ID: <546AD178.9070109@sts.kz> References: <1416160760-16087-1-git-send-email-e_zhumabekov@sts.kz> Mime-Version: 1.0 Content-Type: text/plain; charset="windows-1251" Content-Transfer-Encoding: quoted-printable To: Return-path: In-Reply-To: List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces-VfR2kkLFssw@public.gmane.org Sender: "dev" Sorry, maybe I made a mistake here. Accoring to lib/librte_eal/common/eal_common_cpuflags.c code, it seemed to me that constructor attribute is not supported by intel compiler. So in that case here I decided to leave the code for autodetection. Am I correct? 18.11.2014 9:21, Yerden Zhumabekov =EF=E8=F8=E5=F2: > Initially, SSE4.2 support is detected via CPUID instruction. > > Added rte_hash_crc_set_alg() function to detect and set CRC32 > implementation if necessary. SSE4.2 is allowed by default. If it's > not available, fall back to sw implementation. > > Depending on compiler attributes support, best available algorithm > may be detected upon application startup. > > Signed-off-by: Yerden Zhumabekov > --- > lib/librte_hash/rte_hash_crc.h | 64 ++++++++++++++++++++++++++++++++= ++++++-- > 1 file changed, 62 insertions(+), 2 deletions(-) > > diff --git a/lib/librte_hash/rte_hash_crc.h b/lib/librte_hash/rte_hash_= crc.h > index 15f687a..c1b75e8 100644 > --- a/lib/librte_hash/rte_hash_crc.h > +++ b/lib/librte_hash/rte_hash_crc.h > @@ -45,7 +45,11 @@ extern "C" { > #endif > =20 > #include > +#ifdef RTE_MACHINE_CPUFLAG_SSE4_2 > #include > +#endif > +#include > +#include > =20 > /* Lookup tables for software implementation of CRC32C */ > static uint32_t crc32c_tables[8][256] =3D {{ > @@ -363,8 +367,44 @@ crc32c_2words(uint64_t data, uint32_t init_val) > return crc; > } > =20 > +enum crc32_alg_t { > + CRC32_SW =3D 0, > + CRC32_SSE42, > + CRC32_AUTODETECT > +}; > + > +static enum crc32_alg_t crc32_alg =3D CRC32_AUTODETECT; > + > +/** > + * Allow or disallow use of SSE4.2 instrinsics for CRC32 hash > + * calculation. > + * > + * @param flag > + * unsigned integer flag > + * - (CRC32_SW) Don't use SSE4.2 intrinsics > + * - (CRC32_SSE42) Use SSE4.2 intrinsics if available, set by defaul= t > + */ > +static inline void > +rte_hash_crc_set_alg(enum crc32_alg_t alg) > +{ > + int sse42_supp =3D rte_cpu_get_flag_enabled(RTE_CPUFLAG_SSE4_2); > + enum crc32_alg_t alg_supp =3D sse42_supp ? CRC32_SSE42 : CRC32_SW; > + crc32_alg =3D (alg =3D=3D CRC32_SSE42) ? alg_supp : CRC32_SW; > +} > + > +/* Best available algorithm is detected via CPUID instruction */ > +#ifndef __INTEL_COMPILER > +static inline void __attribute__((constructor)) > +rte_hash_crc_try_sse42(void) > +{ > + rte_hash_crc_set_alg(CRC32_SSE42); > +} > +#endif > + > /** > * Use single crc32 instruction to perform a hash on a 4 byte value. > + * Fall back to software crc32 implementation in case SSE4.2 is > + * not supported > * > * @param data > * Data to perform hash on. > @@ -376,11 +416,22 @@ crc32c_2words(uint64_t data, uint32_t init_val) > static inline uint32_t > rte_hash_crc_4byte(uint32_t data, uint32_t init_val) > { > - return _mm_crc32_u32(init_val, data); > +#ifdef __INTEL_COMPILER > + if (unlikely(crc32_alg =3D=3D CRC32_AUTODETECT)) > + rte_hash_crc_set_alg(CRC32_SSE42); > +#endif > +#ifdef RTE_MACHINE_CPUFLAG_SSE4_2 > + if (likely(crc32_alg =3D=3D CRC32_SSE42)) > + return _mm_crc32_u32(init_val, data); > +#endif > + > + return crc32c_1word(data, init_val); > } > =20 > /** > * Use single crc32 instruction to perform a hash on a 8 byte value. > + * Fall back to software crc32 implementation in case SSE4.2 is > + * not supported > * > * @param data > * Data to perform hash on. > @@ -392,7 +443,16 @@ rte_hash_crc_4byte(uint32_t data, uint32_t init_va= l) > static inline uint32_t > rte_hash_crc_8byte(uint64_t data, uint32_t init_val) > { > - return _mm_crc32_u64(init_val, data); > +#ifdef __INTEL_COMPILER > + if (unlikely(crc32_alg =3D=3D CRC32_AUTODETECT)) > + rte_hash_crc_set_alg(CRC32_SSE42); > +#endif > +#ifdef RTE_MACHINE_CPUFLAG_SSE4_2 > + if (likely(crc32_alg =3D=3D CRC32_SSE42)) > + return _mm_crc32_u64(init_val, data); > +#endif > + > + return crc32c_2words(data, init_val); > } > =20 > /** --=20 Sincerely, Yerden Zhumabekov State Technical Service Astana, KZ