/*
 * 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"

function ff_hscale_8_to_15_neon, export=1
        sbfiz               x7, x6, #1, #32             // filterSize*2 (*2 because int16)
1:      ldr                 w8, [x5], #4                // filterPos[idx]
        ldr                 w0, [x5], #4                // filterPos[idx + 1]
        ldr                 w11, [x5], #4               // filterPos[idx + 2]
        ldr                 w9, [x5], #4                // filterPos[idx + 3]
        mov                 x16, x4                     // filter0 = filter
        add                 x12, x16, x7                // filter1 = filter0 + filterSize*2
        add                 x13, x12, x7                // filter2 = filter1 + filterSize*2
        add                 x4, x13, x7                 // filter3 = filter2 + filterSize*2
        movi                v0.2D, #0                   // val sum part 1 (for dst[0])
        movi                v1.2D, #0                   // val sum part 2 (for dst[1])
        movi                v2.2D, #0                   // val sum part 3 (for dst[2])
        movi                v3.2D, #0                   // val sum part 4 (for dst[3])
        add                 x17, x3, w8, UXTW           // srcp + filterPos[0]
        add                 x8,  x3, w0, UXTW           // srcp + filterPos[1]
        add                 x0, x3, w11, UXTW           // srcp + filterPos[2]
        add                 x11, x3, w9, UXTW           // srcp + filterPos[3]
        mov                 w15, w6                     // filterSize counter
2:      ld1                 {v4.8B}, [x17], #8          // srcp[filterPos[0] + {0..7}]
        ld1                 {v5.8H}, [x16], #16         // load 8x16-bit filter values, part 1
        ld1                 {v6.8B}, [x8], #8           // srcp[filterPos[1] + {0..7}]
        ld1                 {v7.8H}, [x12], #16         // load 8x16-bit at filter+filterSize
        uxtl                v4.8H, v4.8B                // unpack part 1 to 16-bit
        smlal               v0.4S, v4.4H, v5.4H         // v0 accumulates srcp[filterPos[0] + {0..3}] * filter[{0..3}]
        smlal2              v0.4S, v4.8H, v5.8H         // v0 accumulates srcp[filterPos[0] + {4..7}] * filter[{4..7}]
        ld1                 {v8.8B}, [x0], #8           // srcp[filterPos[2] + {0..7}]
        ld1                 {v9.8H}, [x13], #16         // load 8x16-bit at filter+2*filterSize
        uxtl                v6.8H, v6.8B                // unpack part 2 to 16-bit
        smlal               v1.4S, v6.4H, v7.4H         // v1 accumulates srcp[filterPos[1] + {0..3}] * filter[{0..3}]
        uxtl                v8.8H, v8.8B                // unpack part 3 to 16-bit
        smlal               v2.4S, v8.4H, v9.4H         // v2 accumulates srcp[filterPos[2] + {0..3}] * filter[{0..3}]
        smlal2              v2.4S, V8.8H, v9.8H         // v2 accumulates srcp[filterPos[2] + {4..7}] * filter[{4..7}]
        ld1                 {v10.8B}, [x11], #8         // srcp[filterPos[3] + {0..7}]
        smlal2              v1.4S, v6.8H, v7.8H         // v1 accumulates srcp[filterPos[1] + {4..7}] * filter[{4..7}]
        ld1                 {v11.8H}, [x4], #16         // load 8x16-bit at filter+3*filterSize
        subs                w15, w15, #8                // j -= 8: processed 8/filterSize
        uxtl                v10.8H, v10.8B              // unpack part 4 to 16-bit
        smlal               v3.4S, v10.4H, v11.4H       // v3 accumulates srcp[filterPos[3] + {0..3}] * filter[{0..3}]
        smlal2              v3.4S, v10.8H, v11.8H       // v3 accumulates srcp[filterPos[3] + {4..7}] * filter[{4..7}]
        b.gt                2b                          // inner loop if filterSize not consumed completely
        addp                v0.4S, v0.4S, v0.4S         // part0 horizontal pair adding
        addp                v1.4S, v1.4S, v1.4S         // part1 horizontal pair adding
        addp                v2.4S, v2.4S, v2.4S         // part2 horizontal pair adding
        addp                v3.4S, v3.4S, v3.4S         // part3 horizontal pair adding
        addp                v0.4S, v0.4S, v0.4S         // part0 horizontal pair adding
        addp                v1.4S, v1.4S, v1.4S         // part1 horizontal pair adding
        addp                v2.4S, v2.4S, v2.4S         // part2 horizontal pair adding
        addp                v3.4S, v3.4S, v3.4S         // part3 horizontal pair adding
        zip1                v0.4S, v0.4S, v1.4S         // part01 = zip values from part0 and part1
        zip1                v2.4S, v2.4S, v3.4S         // part23 = zip values from part2 and part3
        mov                 v0.d[1], v2.d[0]            // part0123 = zip values from part01 and part23
        subs                w2, w2, #4                  // dstW -= 4
        sqshrn              v0.4H, v0.4S, #7            // shift and clip the 2x16-bit final values
        st1                 {v0.4H}, [x1], #8           // write to destination part0123
        b.gt                1b                          // loop until end of line
        ret
endfunc