/*
 * Copyright (c) 2016 Matthieu Bouron <matthieu.bouron stupeflix.com>
 * Copyright (c) 2016 Clément Bœsch <clement stupeflix.com>
 *
 * This file is part of FFmpeg.
 *
 * FFmpeg is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * FFmpeg is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with FFmpeg; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

#include "libavutil/aarch64/asm.S"

.macro load_yoff_ycoeff yoff ycoeff
#if defined(__APPLE__)
    ldp                 w9, w10, [sp, #\yoff]
#else
    ldr                 w9,  [sp, #\yoff]
    ldr                 w10, [sp, #\ycoeff]
#endif
.endm

.macro load_args_nv12
    ldr                 x8,  [sp]                                       // table
    load_yoff_ycoeff    8, 16                                           // y_offset, y_coeff
    ld1                 {v1.1D}, [x8]
    dup                 v0.8H, w10
    dup                 v3.8H, w9
    sub                 w3, w3, w0, lsl #2                              // w3 = linesize  - width * 4 (padding)
    sub                 w5, w5, w0                                      // w5 = linesizeY - width     (paddingY)
    sub                 w7, w7, w0                                      // w7 = linesizeC - width     (paddingC)
    neg                 w11, w0
.endm

.macro load_args_nv21
    load_args_nv12
.endm

.macro load_args_yuv420p
    ldr                 x13, [sp]                                       // srcV
    ldr                 w14, [sp, #8]                                   // linesizeV
    ldr                 x8,  [sp, #16]                                  // table
    load_yoff_ycoeff    24, 32                                          // y_offset, y_coeff
    ld1                 {v1.1D}, [x8]
    dup                 v0.8H, w10
    dup                 v3.8H, w9
    sub                 w3, w3, w0, lsl #2                              // w3 = linesize  - width * 4 (padding)
    sub                 w5, w5, w0                                      // w5 = linesizeY - width     (paddingY)
    sub                 w7,  w7,  w0, lsr #1                            // w7  = linesizeU - width / 2 (paddingU)
    sub                 w14, w14, w0, lsr #1                            // w14 = linesizeV - width / 2 (paddingV)
    lsr                 w11, w0, #1
    neg                 w11, w11
.endm

.macro load_args_yuv422p
    ldr                 x13, [sp]                                       // srcV
    ldr                 w14, [sp, #8]                                   // linesizeV
    ldr                 x8,  [sp, #16]                                  // table
    load_yoff_ycoeff    24, 32                                          // y_offset, y_coeff
    ld1                 {v1.1D}, [x8]
    dup                 v0.8H, w10
    dup                 v3.8H, w9
    sub                 w3, w3, w0, lsl #2                              // w3 = linesize  - width * 4 (padding)
    sub                 w5, w5, w0                                      // w5 = linesizeY - width     (paddingY)
    sub                 w7,  w7,  w0, lsr #1                            // w7  = linesizeU - width / 2 (paddingU)
    sub                 w14, w14, w0, lsr #1                            // w14 = linesizeV - width / 2 (paddingV)
.endm

.macro load_chroma_nv12
    ld2                 {v16.8B, v17.8B}, [x6], #16
    ushll               v18.8H, v16.8B, #3
    ushll               v19.8H, v17.8B, #3
.endm

.macro load_chroma_nv21
    ld2                 {v16.8B, v17.8B}, [x6], #16
    ushll               v19.8H, v16.8B, #3
    ushll               v18.8H, v17.8B, #3
.endm

.macro load_chroma_yuv420p
    ld1                 {v16.8B}, [ x6], #8
    ld1                 {v17.8B}, [x13], #8
    ushll               v18.8H, v16.8B, #3
    ushll               v19.8H, v17.8B, #3
.endm

.macro load_chroma_yuv422p
    load_chroma_yuv420p
.endm

.macro increment_nv12
    ands                w15, w1, #1
    csel                w16, w7, w11, ne                                // incC = (h & 1) ? paddincC : -width
    add                 x6,  x6, w16, SXTW                              // srcC += incC
.endm

.macro increment_nv21
    increment_nv12
.endm

.macro increment_yuv420p
    ands                w15, w1, #1
    csel                w16,  w7, w11, ne                               // incU = (h & 1) ? paddincU : -width/2
    csel                w17, w14, w11, ne                               // incV = (h & 1) ? paddincV : -width/2
    add                 x6,  x6,  w16, SXTW                             // srcU += incU
    add                 x13, x13, w17, SXTW                             // srcV += incV
.endm

.macro increment_yuv422p
    add                 x6,  x6,  w7, UXTW                              // srcU += incU
    add                 x13, x13, w14, UXTW                             // srcV += incV
.endm

.macro compute_rgba r1 g1 b1 a1 r2 g2 b2 a2
    add                 v20.8H, v26.8H, v20.8H                          // Y1 + R1
    add                 v21.8H, v27.8H, v21.8H                          // Y2 + R2
    add                 v22.8H, v26.8H, v22.8H                          // Y1 + G1
    add                 v23.8H, v27.8H, v23.8H                          // Y2 + G2
    add                 v24.8H, v26.8H, v24.8H                          // Y1 + B1
    add                 v25.8H, v27.8H, v25.8H                          // Y2 + B2
    sqrshrun            \r1, v20.8H, #1                                 // clip_u8((Y1 + R1) >> 1)
    sqrshrun            \r2, v21.8H, #1                                 // clip_u8((Y2 + R1) >> 1)
    sqrshrun            \g1, v22.8H, #1                                 // clip_u8((Y1 + G1) >> 1)
    sqrshrun            \g2, v23.8H, #1                                 // clip_u8((Y2 + G1) >> 1)
    sqrshrun            \b1, v24.8H, #1                                 // clip_u8((Y1 + B1) >> 1)
    sqrshrun            \b2, v25.8H, #1                                 // clip_u8((Y2 + B1) >> 1)
    movi                \a1, #255
    movi                \a2, #255
.endm

.macro declare_func ifmt ofmt
function ff_\ifmt\()_to_\ofmt\()_neon, export=1
    load_args_\ifmt
1:
    mov                 w8, w0                                          // w8 = width
2:
    movi                v5.8H, #4, lsl #8                               // 128 * (1<<3)
    load_chroma_\ifmt
    sub                 v18.8H, v18.8H, v5.8H                           // U*(1<<3) - 128*(1<<3)
    sub                 v19.8H, v19.8H, v5.8H                           // V*(1<<3) - 128*(1<<3)
    sqdmulh             v20.8H, v19.8H, v1.H[0]                         // V * v2r            (R)
    sqdmulh             v22.8H, v18.8H, v1.H[1]                         // U * u2g
    sqdmulh             v19.8H, v19.8H, v1.H[2]                         //           V * v2g
    add                 v22.8H, v22.8H, v19.8H                          // U * u2g + V * v2g  (G)
    sqdmulh             v24.8H, v18.8H, v1.H[3]                         // U * u2b            (B)
    zip2                v21.8H, v20.8H, v20.8H                          // R2
    zip1                v20.8H, v20.8H, v20.8H                          // R1
    zip2                v23.8H, v22.8H, v22.8H                          // G2
    zip1                v22.8H, v22.8H, v22.8H                          // G1
    zip2                v25.8H, v24.8H, v24.8H                          // B2
    zip1                v24.8H, v24.8H, v24.8H                          // B1
    ld1                 {v2.16B}, [x4], #16                             // load luma
    ushll               v26.8H, v2.8B,  #3                              // Y1*(1<<3)
    ushll2              v27.8H, v2.16B, #3                              // Y2*(1<<3)
    sub                 v26.8H, v26.8H, v3.8H                           // Y1*(1<<3) - y_offset
    sub                 v27.8H, v27.8H, v3.8H                           // Y2*(1<<3) - y_offset
    sqdmulh             v26.8H, v26.8H, v0.8H                           // ((Y1*(1<<3) - y_offset) * y_coeff) >> 15
    sqdmulh             v27.8H, v27.8H, v0.8H                           // ((Y2*(1<<3) - y_offset) * y_coeff) >> 15

.ifc \ofmt,argb // 1 2 3 0
    compute_rgba        v5.8B,v6.8B,v7.8B,v4.8B, v17.8B,v18.8B,v19.8B,v16.8B
.endif

.ifc \ofmt,rgba // 0 1 2 3
    compute_rgba        v4.8B,v5.8B,v6.8B,v7.8B, v16.8B,v17.8B,v18.8B,v19.8B
.endif

.ifc \ofmt,abgr // 3 2 1 0
    compute_rgba        v7.8B,v6.8B,v5.8B,v4.8B, v19.8B,v18.8B,v17.8B,v16.8B
.endif

.ifc \ofmt,bgra // 2 1 0 3
    compute_rgba        v6.8B,v5.8B,v4.8B,v7.8B, v18.8B,v17.8B,v16.8B,v19.8B
.endif

    st4                 { v4.8B, v5.8B, v6.8B, v7.8B}, [x2], #32
    st4                 {v16.8B,v17.8B,v18.8B,v19.8B}, [x2], #32
    subs                w8, w8, #16                                     // width -= 16
    b.gt                2b
    add                 x2, x2, w3, UXTW                                // dst  += padding
    add                 x4, x4, w5, UXTW                                // srcY += paddingY
    increment_\ifmt
    subs                w1, w1, #1                                      // height -= 1
    b.gt                1b
    ret
endfunc
.endm

.macro declare_rgb_funcs ifmt
    declare_func \ifmt, argb
    declare_func \ifmt, rgba
    declare_func \ifmt, abgr
    declare_func \ifmt, bgra
.endm

declare_rgb_funcs nv12
declare_rgb_funcs nv21
declare_rgb_funcs yuv420p
declare_rgb_funcs yuv422p