How fast can you make linear search?

Question

I\'m looking to optimize this linear search:

static int
linear (const int *arr, int n, int key)
{
        int i = 0;
        while (i < n) {
                      


        

Answer 1

uint32 LinearFindSse4( uint8* data, size_t data_len, uint8* finddata, size_t finddatalen )
{
    /**
     * the following is based on...
     * #define haszero(v) (((v) - 0x01010101UL) & ~(v) & 0x80808080UL)
     * we split it into 2 sections
     * first section is:
     * (v) - 0x01010101UL)
     *
     * second section is:
     * ~(v) & 0x80808080UL)
     */
    __m128i ones = _mm_set1_epi8( 0x01 );
    __m128i eights = _mm_set1_epi8( 0x80 );
    __m128i find_field = _mm_set1_epi8( finddata[0] );

    uint32 found_at = 0;
    for (int i = 0; i < data_len; i+=16)
    {
#define CHECKTHIS( n ) if (!memcmp(&data[i+n], &finddata[0], sizeof(finddata))) { found_at = i + n; break; }

        __m128i chunk = _mm_stream_load_si128( (__m128i *)&data[i] );
        __m128i xor_result = _mm_xor_si128( chunk, find_field );
        __m128i first_sec = _mm_sub_epi64( xor_result, ones );
        __m128i second_sec = _mm_andnot_si128( xor_result, eights );

        if(!_mm_testz_si128(first_sec, second_sec))
        {
            CHECKTHIS(0);
            CHECKTHIS(1);
            CHECKTHIS(2);
            CHECKTHIS(3);
            CHECKTHIS(4);
            CHECKTHIS(5);
            CHECKTHIS(6);
            CHECKTHIS(7);
            CHECKTHIS(8);
            CHECKTHIS(9);
            CHECKTHIS(10);
            CHECKTHIS(11);
            CHECKTHIS(12);
            CHECKTHIS(13);
            CHECKTHIS(14);
            CHECKTHIS(15);
        }
    }
    return found_at;
}