#version 450

#include "types.comp"
#include "generic_unary_head.comp"

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

uint src0_idx_mod(uint idx) {
    const uint i13 = idx / (p.ne12*p.ne11*p.ne10);
    const uint i13_offset = i13 * p.ne12*p.ne11*p.ne10;
    const uint i12 = (idx - i13_offset) / (p.ne11*p.ne10);
    const uint i12_offset = i12*p.ne11*p.ne10;
    const uint i11 = (idx - i13_offset - i12_offset) / p.ne10;
    const uint i10 = idx - i13_offset - i12_offset - i11*p.ne10;
    return (i13 % p.ne03)*p.nb03 + (i12 % p.ne02)*p.nb02 + (i11 % p.ne01)*p.nb01 + (i10 % p.ne00)*p.nb00;
}

void main() {
    const uint idx = get_idx();

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

    data_d[p.d_offset + dst_idx(idx)] = D_TYPE(data_a[src0_idx_mod(idx)]);
}