Re: [dpdk-dev] [PATCH v4 3/5] hash: add fallback to software CRC32 implementation

[Neil Horman <nhorman@tuxdriver.com>]

On Tue, Nov 18, 2014 at 08:03:40PM +0600, Yerden Zhumabekov wrote:
> 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.
> 
> Best available algorithm is detected upon application startup
> through the constructor function rte_hash_crc_try_sse442().
> 
> Signed-off-by: Yerden Zhumabekov <e_zhumabekov@sts.kz>
> ---
>  lib/librte_hash/rte_hash_crc.h |   53 ++++++++++++++++++++++++++++++++++++++--
>  1 file changed, 51 insertions(+), 2 deletions(-)
> 
> diff --git a/lib/librte_hash/rte_hash_crc.h b/lib/librte_hash/rte_hash_crc.h
> index 15f687a..332ed99 100644
> --- a/lib/librte_hash/rte_hash_crc.h
> +++ b/lib/librte_hash/rte_hash_crc.h
> @@ -45,7 +45,11 @@ extern "C" {
>  #endif
>  
>  #include <stdint.h>
> +#ifdef RTE_MACHINE_CPUFLAG_SSE4_2
>  #include <nmmintrin.h>
> +#endif
> +#include <rte_cpuflags.h>
> +#include <rte_branch_prediction.h>
>  
>  /* Lookup tables for software implementation of CRC32C */
>  static uint32_t crc32c_tables[8][256] = {{
> @@ -363,8 +367,41 @@ crc32c_2words(uint64_t data, uint32_t init_val)
>  	return crc;
>  }
>  
> +enum crc32_alg_t {
> +	CRC32_SW = 0,
> +	CRC32_SSE42
> +};
> +
> +static enum crc32_alg_t crc32_alg;
> +
> +/**
> + * 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 default
> + */
> +static inline void
> +rte_hash_crc_set_alg(enum crc32_alg_t alg)
> +{
> +	int sse42_supp = rte_cpu_get_flag_enabled(RTE_CPUFLAG_SSE4_2);
> +	enum crc32_alg_t alg_supp = sse42_supp ? CRC32_SSE42 : CRC32_SW;
> +	crc32_alg = (alg == CRC32_SSE42) ? alg_supp : CRC32_SW;
> +}
> +
> +/* Best available algorithm is detected via CPUID instruction */
> +static inline void __attribute__((constructor))
> +rte_hash_crc_try_sse42(void)
> +{
> +	rte_hash_crc_set_alg(CRC32_SSE42);
> +}
> +
>  /**
>   * 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 +413,18 @@ 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 RTE_MACHINE_CPUFLAG_SSE4_2
> +	if (likely(crc32_alg == CRC32_SSE42))
> +		return _mm_crc32_u32(init_val, data);
> +#endif

you don't really need these ifdefs here anymore given that you have a
constructor to do the algorithm selection.  In fact you need to remove them, in
the event you build on a system that doesn't support SSE42, but run on a system
that does.

Neil