/*
 *  Copyright (c) 2010 The WebM project authors. All Rights Reserved.
 *
 *  Use of this source code is governed by a BSD-style license
 *  that can be found in the LICENSE file in the root of the source
 *  tree. An additional intellectual property rights grant can be found
 *  in the file PATENTS.  All contributing project authors may
 *  be found in the AUTHORS file in the root of the source tree.
 */

#include "vpx_rtcd.h"

#ifdef RVL
#   define POWERPC_IDCT4X4_OPTIMS
#endif

/****************************************************************************
 * Notes:
 *
 * This implementation makes use of 16 bit fixed point verio of two multiply
 * constants:
 *         1.   sqrt(2) * cos (pi/8)
 *         2.   sqrt(2) * sin (pi/8)
 * Becuase the first constant is bigger than 1, to maintain the same 16 bit
 * fixed point precision as the second one, we use a trick of
 *         x * a = x + x*(a-1)
 * so
 *         x * sqrt(2) * cos (pi/8) = x + x * (sqrt(2) *cos(pi/8)-1).
 **************************************************************************/
static const int cospi8sqrt2minus1 = 20091;
static const int sinpi8sqrt2      = 35468;

#ifdef POWERPC_IDCT4X4_OPTIMS

/*#define IDCT4X4_LOAD_TWO_PACKED_SHORTS(index0, index1) \
    asm \
    { \
        lwzu i##index0, 4(input); \
        clrlwi i##index1, i##index0, 16; \
        srawi i##index0, i##index0, 16; \
        extsh i##index1, i##index1; \
    }; \*/


#define IDCT4X4_PROCESS_LINE(index0, index1, index2, index3) \
    a1 = i##index0 + i##index2; \
    b1 = i##index0 - i##index2; \
     \
    temp1 = (i##index1 * sinpi8sqrt2) >> 16; \
    temp2 = i##index3 + ((i##index3 * cospi8sqrt2minus1) >> 16); \
    c1 = temp1 - temp2; \
     \
    temp1 = i##index1 + ((i##index1 * cospi8sqrt2minus1) >> 16); \
    temp2 = (i##index3 * sinpi8sqrt2) >> 16; \
    d1 = temp1 + temp2; \
     \
    i##index0 = a1 + d1; \
    i##index3 = a1 - d1; \
     \
    i##index1 = b1 + c1; \
    i##index2 = b1 - c1; \


#define IDCT4X4_ADD_PREDICTION_AND_CLAMP(index) \
    addi i##index, i##index, 4; \
    srawi i##index, i##index, 3; \
    srwi prediction, rowPrediction, 24; \
    add. i##index, i##index, prediction; \
    slwi rowPrediction, rowPrediction, 8; \
    bge positive##index; \
    li i##index, 0; \
positive##index: \
    cmpwi i##index, 0xff; \
    blt under255##index; \
    li i##index, 0xff; \
under255##index: \
    slwi rowOutput, rowOutput, 8; \
    or rowOutput, rowOutput, i##index; \


#define IDCT4X4_OUTPUT_LINE(index0, index1, index2, index3) \
    asm \
    { \
        lwz rowPrediction, 0(pred_ptr); \
        IDCT4X4_ADD_PREDICTION_AND_CLAMP(index0); \
        IDCT4X4_ADD_PREDICTION_AND_CLAMP(index1); \
        IDCT4X4_ADD_PREDICTION_AND_CLAMP(index2); \
        IDCT4X4_ADD_PREDICTION_AND_CLAMP(index3); \
        stw rowOutput, 0(dst_ptr); \
    }; \
    dst_ptr += dst_stride; \
    pred_ptr += pred_stride; \


void vp8_short_idct4x4llm_c(register short *input, register unsigned char *pred_ptr,
                            register int pred_stride, register unsigned char *dst_ptr,
                            register int dst_stride)
{
    register int a1, b1, c1, d1;
    register int temp1, temp2;

    register i0, i1, i2, i3;
    register i4, i5, i6, i7;
    register i8, i9, i10, i11;
    register i12, i13, i14, i15;

    register rowPrediction, prediction;
    register rowOutput;
    
    // this one is not faster, but may be improved to become so
    /*input -= 2;
    IDCT4X4_LOAD_TWO_PACKED_SHORTS(0, 1);
    IDCT4X4_LOAD_TWO_PACKED_SHORTS(2, 3);
    IDCT4X4_LOAD_TWO_PACKED_SHORTS(4, 5);
    IDCT4X4_LOAD_TWO_PACKED_SHORTS(6, 7);
    IDCT4X4_LOAD_TWO_PACKED_SHORTS(8, 9);
    IDCT4X4_LOAD_TWO_PACKED_SHORTS(10, 11);
    IDCT4X4_LOAD_TWO_PACKED_SHORTS(12, 13);
    IDCT4X4_LOAD_TWO_PACKED_SHORTS(14, 15);*/

    i0 = input[0];
    i1 = input[1];
    i2 = input[2];
    i3 = input[3];
    i4 = input[4];
    i5 = input[5];
    i6 = input[6];
    i7 = input[7];
    i8 = input[8];
    i9 = input[9];
    i10 = input[10];
    i11 = input[11];
    i12 = input[12];
    i13 = input[13];
    i14 = input[14];
    i15 = input[15];
    
    // columns
    IDCT4X4_PROCESS_LINE(0, 4, 8, 12);
    IDCT4X4_PROCESS_LINE(1, 5, 9, 13);
    IDCT4X4_PROCESS_LINE(2, 6, 10, 14);
    IDCT4X4_PROCESS_LINE(3, 7, 11, 15);

    // rows
    IDCT4X4_PROCESS_LINE(0, 1, 2, 3);
    IDCT4X4_OUTPUT_LINE (0, 1, 2, 3);
    IDCT4X4_PROCESS_LINE(4, 5, 6, 7);
    IDCT4X4_OUTPUT_LINE (4, 5, 6, 7);
    IDCT4X4_PROCESS_LINE(8, 9, 10, 11);
    IDCT4X4_OUTPUT_LINE (8, 9, 10, 11);
    IDCT4X4_PROCESS_LINE(12, 13, 14, 15);
    IDCT4X4_OUTPUT_LINE (12, 13, 14, 15);
}

#else // POWERPC_IDCT4X4_OPTIMS

void vp8_short_idct4x4llm_c(short *input, unsigned char *pred_ptr,
                            int pred_stride, unsigned char *dst_ptr,
                            int dst_stride)
{
    int i;
    int r, c;
    int a1, b1, c1, d1;
    short output[16];
    short *ip = input;
    short *op = output;
    int temp1, temp2;
    int shortpitch = 4;

    for (i = 0; i < 4; i++)
    {
        a1 = ip[0] + ip[8];
        b1 = ip[0] - ip[8];

        temp1 = (ip[4] * sinpi8sqrt2) >> 16;
        temp2 = ip[12] + ((ip[12] * cospi8sqrt2minus1) >> 16);
        c1 = temp1 - temp2;

        temp1 = ip[4] + ((ip[4] * cospi8sqrt2minus1) >> 16);
        temp2 = (ip[12] * sinpi8sqrt2) >> 16;
        d1 = temp1 + temp2;

        op[shortpitch*0] = a1 + d1;
        op[shortpitch*3] = a1 - d1;

        op[shortpitch*1] = b1 + c1;
        op[shortpitch*2] = b1 - c1;

        ip++;
        op++;
    }

    ip = output;
    op = output;

    for (i = 0; i < 4; i++)
    {
        a1 = ip[0] + ip[2];
        b1 = ip[0] - ip[2];

        temp1 = (ip[1] * sinpi8sqrt2) >> 16;
        temp2 = ip[3] + ((ip[3] * cospi8sqrt2minus1) >> 16);
        c1 = temp1 - temp2;

        temp1 = ip[1] + ((ip[1] * cospi8sqrt2minus1) >> 16);
        temp2 = (ip[3] * sinpi8sqrt2) >> 16;
        d1 = temp1 + temp2;


        op[0] = (a1 + d1 + 4) >> 3;
        op[3] = (a1 - d1 + 4) >> 3;

        op[1] = (b1 + c1 + 4) >> 3;
        op[2] = (b1 - c1 + 4) >> 3;

        ip += shortpitch;
        op += shortpitch;
    }

    ip = output;
    for (r = 0; r < 4; r++)
    {
        for (c = 0; c < 4; c++)
        {
            int a = ip[c] + pred_ptr[c] ;

            if (a < 0)
                a = 0;

            if (a > 255)
                a = 255;

            dst_ptr[c] = (unsigned char) a ;
        }
        ip += 4;
        dst_ptr += dst_stride;
        pred_ptr += pred_stride;
    }
}

#endif // POWERPC_IDCT4X4_OPTIMS

void vp8_dc_only_idct_add_c(short input_dc, unsigned char *pred_ptr,
                            int pred_stride, unsigned char *dst_ptr,
                            int dst_stride)
{
    int a1 = ((input_dc + 4) >> 3);
    int r, c;

    for (r = 0; r < 4; r++)
    {
        for (c = 0; c < 4; c++)
        {
            int a = a1 + pred_ptr[c] ;

            if (a < 0)
                a = 0;

            if (a > 255)
                a = 255;

            dst_ptr[c] = (unsigned char) a ;
        }

        dst_ptr += dst_stride;
        pred_ptr += pred_stride;
    }

}

void vp8_short_inv_walsh4x4_c(short *input, short *mb_dqcoeff)
{
    short output[16];
    int i;
    int a1, b1, c1, d1;
    int a2, b2, c2, d2;
    short *ip = input;
    short *op = output;

    for (i = 0; i < 4; i++)
    {
        a1 = ip[0] + ip[12];
        b1 = ip[4] + ip[8];
        c1 = ip[4] - ip[8];
        d1 = ip[0] - ip[12];

        op[0] = a1 + b1;
        op[4] = c1 + d1;
        op[8] = a1 - b1;
        op[12] = d1 - c1;
        ip++;
        op++;
    }

    ip = output;
    op = output;

    for (i = 0; i < 4; i++)
    {
        a1 = ip[0] + ip[3];
        b1 = ip[1] + ip[2];
        c1 = ip[1] - ip[2];
        d1 = ip[0] - ip[3];

        a2 = a1 + b1;
        b2 = c1 + d1;
        c2 = a1 - b1;
        d2 = d1 - c1;

        op[0] = (a2 + 3) >> 3;
        op[1] = (b2 + 3) >> 3;
        op[2] = (c2 + 3) >> 3;
        op[3] = (d2 + 3) >> 3;

        ip += 4;
        op += 4;
    }

    for(i = 0; i < 16; i++)
    {
        mb_dqcoeff[i * 16] = output[i];
    }
}

void vp8_short_inv_walsh4x4_1_c(short *input, short *mb_dqcoeff)
{
    int i;
    int a1;

    a1 = ((input[0] + 3) >> 3);
    for(i = 0; i < 16; i++)
    {
        mb_dqcoeff[i * 16] = a1;
    }
}

void vp8_idct_dequant_0_1x_c(short* q, short* dq, unsigned char* dst, int dst_stride)
{
	vp8_dc_only_idct_add(q[0]*dq[0], dst, dst_stride, dst, dst_stride);
	q[0] = 0;
}