Function std::rocm_upsample2x_concat

int rocm_upsample2x_concat(
    struct RocmBuf x,
    unsigned long xChannels,
    struct RocmBuf skip,
    unsigned long skipChannels,
    struct RocmBuf out,
    unsigned long batch,
    unsigned long h,
    unsigned long w,
)

out[b] = (x[b].upsample2x_nearest(), skip[b]) along channels, in one pass: x is [batch, xChannels, h, w], skip [batch, skipChannels, 2h, 2w], out [batch, xChannels + skipChannels, 2h, 2w] (a U-Net decoder step).