#version 450

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

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;
    }

#if defined(DATA_D_BF16)
    float f = float(data_a[get_aoffset() + src0_idx(idx)]);
    data_d[get_doffset() + dst_idx(idx)] = D_TYPE(fp32_to_bf16(f));
#elif !defined(OPTIMIZATION_ERROR_WORKAROUND)
    data_d[get_doffset() + dst_idx(idx)] = D_TYPE(data_a[get_aoffset() + src0_idx(idx)]);
#else
    data_d[get_doffset() + dst_idx(idx)] = data_a[get_aoffset() + src0_idx(idx)];
#endif
}