// daedalus-fourier — H.264 luma qpel mc02 (8x8, vertical half-pel), V3D 7.1.
//
// Sibling of cycle 9's v3d_h264_qpel_mc20.comp.  Same 6-tap filter,
// transposed to vertical direction:
//
//   dst[r,c] = clip255(
//       ( s[r-2,c]
//         - 5 * s[r-1,c]
//         + 20 * s[r,  c]
//         + 20 * s[r+1,c]
//         -  5 * s[r+2,c]
//         +      s[r+3,c]
//         + 16
//       ) >> 5)
//
// src+src_off points at row 0 col 0 of the OUTPUT block; the filter
// reads rows -2..+3 (2 rows of top context, 3 rows of bottom).
//
// Same WG layout as mc20: 64 lanes / 1 block-per-WG / 1 lane-per-pixel.
//
// License: BSD-2-Clause.

#version 450
#extension GL_EXT_shader_8bit_storage             : require
#extension GL_EXT_shader_explicit_arithmetic_types : require

layout(local_size_x = 64, local_size_y = 1, local_size_z = 1) in;

layout(binding = 0) readonly buffer Src { uint8_t src[]; } u_src;
layout(binding = 1) buffer Dst { uint8_t dst[]; } u_dst;
layout(binding = 2) readonly buffer Meta { uvec4 meta[]; } u_meta;

layout(push_constant) uniform PC {
    uint n_blocks;
    uint stride_u8;
    uint _pad0, _pad1;
} pc;

void main()
{
    uint block_idx = gl_WorkGroupID.x;
    if (block_idx >= pc.n_blocks) return;

    uint lane = gl_LocalInvocationID.x;
    uint r = lane >> 3;
    uint c = lane & 7u;

    uint dst_off = u_meta.meta[block_idx].x;
    uint src_off = u_meta.meta[block_idx].y;
    uint stride  = pc.stride_u8;

    // Read the 6 rows of vertical context at col (c) of THIS output row.
    // src_off+r*stride+c is at the OUTPUT pixel position; the kernel
    // samples r-2..r+3 along the column.  Unsigned-safe because the
    // public API contract guarantees src_off >= 2*stride.
    uint col_base = src_off + c;

    int s_m2 = int(u_src.src[col_base + (r - 2u) * stride]);
    int s_m1 = int(u_src.src[col_base + (r - 1u) * stride]);
    int s_0  = int(u_src.src[col_base +  r       * stride]);
    int s_p1 = int(u_src.src[col_base + (r + 1u) * stride]);
    int s_p2 = int(u_src.src[col_base + (r + 2u) * stride]);
    int s_p3 = int(u_src.src[col_base + (r + 3u) * stride]);

    int v = s_m2 - 5 * s_m1 + 20 * s_0 + 20 * s_p1 - 5 * s_p2 + s_p3 + 16;
    int p = clamp(v >> 5, 0, 255);

    u_dst.dst[dst_off + r * stride + c] = uint8_t(p);
}