Trait std::RocmTensor

trait RocmTensor : DeviceTensor {
    unsigned long device_buffer() const;
}

One trait per GPU backend, each inheriting DeviceTensor: code written for one backend's buffers (a hand-written kernel, a vendor library call) asks for its tensor. device_buffer() is the values' buffer on that backend -- a hipDeviceptr, a CUdeviceptr, an MTLBuffer's GPU address, a Vulkan buffer device address -- and 0 while the tensor is elsewhere: check device() first, or place() it.