Historically, CPUs have used hardware-managed caches but the earlier GPUs only provided software-managed local memories. However, as GPUs are being increasingly used for general-purpose applications, state-of-the-art GPUs are being designed with hardware-managed multi-level caches  which have helped the GPUs to move towards mainstream computing. For example, GeForce 200 series GT200 architecture GPUs did not feature an L2 cache, the Fermi GPU has 768 KB last-level cache, the Kepler GPU has 1536 KB last-level cache,   the Maxwell GPU has 2048 KB last-level cache and the Pascal GPU has 4096 KB last-level cache.
Students following one of the specialised MEng courses will select some of their options from a group of advanced courses set down for that specialisation. All MEng courses include an approved period of professional formation - this will be either industrial placement, extended project work or placement in a European industry or university. It takes place during the period between Easter and the start of the fourth year. The Computing Integrated Engineering Study Scheme has been developed to satisfy the requirements set down by the engineering institutions.