#version 450

#include "types.glsl"
#include "generic_unary_head.glsl" // included to use functions like fastdiv etc.

layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;

void main() {

    const uint idx = get_idx();

    if (idx >= p.ne) {
        return;
    }

    const uint p0 = floatBitsToUint(p.param1);
    const uint p1 = floatBitsToUint(p.param2);

    const uint i3 = fastdiv(idx, p.ne1_012mp, fastdiv_L(p.ne1_Ls, 0));
    const uint i3_offset = i3 * p.ne12 * p.ne11 * p.ne10;

    const uint i2 = fastdiv(idx - i3_offset, p.ne1_01mp, fastdiv_L(p.ne1_Ls, 1));
    const uint i2_offset = i2 * p.ne11 * p.ne10;

    const uint i1 = fastdiv(idx - i3_offset - i2_offset, p.ne1_0mp, fastdiv_L(p.ne1_Ls, 2));
    const uint i0 = idx - i3_offset - i2_offset - i1 * p.ne10;

    uint src_col;

    if (i0 < p0) {
        src_col = p0 - i0;    // left pad area
    } else if (i0 < p0 + p.ne00) {
        src_col = i0 - p0;    // center area
    } else {
        src_col = 2u * p.ne00 - 2u - (i0 - p0);  // right pad area
    }

    const uint src_idx = i3 * p.nb03 + i2 * p.nb02 + i1 * p.nb01 + src_col * p.nb00;
    const uint d_idx = i3 * p.nb13 + i2 * p.nb12 + i1 * p.nb11 + i0 * p.nb10;

    // copy the computed value to the destination tensor
    data_d[get_doffset() + d_idx] = D_TYPE(data_a[get_aoffset() + src_idx]);
}