XXH_FORCE_INLINE xxh_u64 XXH3_mix16B()

in include/hash/xxhash.h [2884:2914]

• 16 lines of code
• 5 McCabe index (conditional complexity)

XXH_FORCE_INLINE xxh_u64 XXH3_mix16B(const xxh_u8* XXH_RESTRICT input,
                                     const xxh_u8* XXH_RESTRICT secret, xxh_u64 seed64)
{
#if defined(__GNUC__) && !defined(__clang__) /* GCC, not Clang */ \
  && defined(__i386__) && defined(__SSE2__)  /* x86 + SSE2 */ \
  && !defined(XXH_ENABLE_AUTOVECTORIZE)      /* Define to disable like XXH32 hack */
    /*
     * UGLY HACK:
     * GCC for x86 tends to autovectorize the 128-bit multiply, resulting in
     * slower code.
     *
     * By forcing seed64 into a register, we disrupt the cost model and
     * cause it to scalarize. See `XXH32_round()`
     *
     * FIXME: Clang's output is still _much_ faster -- On an AMD Ryzen 3600,
     * XXH3_64bits @ len=240 runs at 4.6 GB/s with Clang 9, but 3.3 GB/s on
     * GCC 9.2, despite both emitting scalar code.
     *
     * GCC generates much better scalar code than Clang for the rest of XXH3,
     * which is why finding a more optimal codepath is an interest.
     */
    __asm__ ("" : "+r" (seed64));
#endif
    {   xxh_u64 const input_lo = XXH_readLE64(input);
        xxh_u64 const input_hi = XXH_readLE64(input+8);
        return XXH3_mul128_fold64(
            input_lo ^ (XXH_readLE64(secret)   + seed64),
            input_hi ^ (XXH_readLE64(secret+8) - seed64)
        );
    }
}