1 /*

     2  * Copyright (c) 2005

     3  *	Eric Anholt.  All rights reserved.

     4  *

     5  * Redistribution and use in source and binary forms, with or without

     6  * modification, are permitted provided that the following conditions

     7  * are met:

     8  * 1. Redistributions of source code must retain the above copyright

     9  *    notice, this list of conditions and the following disclaimer.

    10  * 2. Redistributions in binary form must reproduce the above copyright

    11  *    notice, this list of conditions and the following disclaimer in the

    12  *    documentation and/or other materials provided with the distribution.

    13  *

    14  * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND

    15  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE

    16  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE

    17  * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR BE LIABLE

    18  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL

    19  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS

    20  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)

    21  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT

    22  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY

    23  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF

    24  * SUCH DAMAGE.

    25  */

    26 

    27 #ifdef HAVE_CONFIG_H

    28 #include "config.h"

    29 #endif

    30 #include <liboil/liboilclasses.h>

    31 #include <liboil/liboilfunction.h>

    32 #include <emmintrin.h>

    33 

    34 #define SSE_FUNCTION __attribute__((force_align_arg_pointer))

    35 

    36 #ifdef ENABLE_BROKEN_IMPLS

    37 union m128_int {

    38   __m128i m128;

    39   uint32_t i[4];

    40   uint16_t s[8];

    41 };

    42 

    43 SSE_FUNCTION static void

    44 sad8x8_u8_sse (uint32_t *dest, uint8_t *src1, int sstr1, uint8_t *src2,

    45     int sstr2)

    46 {

    47   int i;

    48   __m128i sum = _mm_setzero_si128();

    49   union m128_int sumi;

    50 

    51   for (i = 0; i < 4; i++) {

    52     __m128i xmm0, xmm1, xmm2, xmm3;

    53     xmm0 = _mm_loadl_epi64((__m128i *)src1);

    54     xmm1 = _mm_loadl_epi64((__m128i *)(src1 + sstr1));

    55     xmm2 = _mm_loadl_epi64((__m128i *)src2);

    56     xmm3 = _mm_loadl_epi64((__m128i *)(src2 + sstr2));

    57     xmm0 = _mm_unpacklo_epi8(xmm0, xmm1);

    58     xmm2 = _mm_unpacklo_epi8(xmm2, xmm3);

    59     sum = _mm_add_epi64(sum, _mm_sad_epu8(xmm0, xmm2));

    60     src1 += 2 * sstr1;

    61     src2 += 2 * sstr2;

    62   }

    63   sumi.m128 = sum;

    64   *dest = sumi.i[0] + sumi.i[2];

    65 }

    66 OIL_DEFINE_IMPL_FULL_WRAPPER(sad8x8_u8_sse, sad8x8_u8, OIL_IMPL_FLAG_SSE2);

    67 #endif

    68