Abstract: A method and system to perform caching based at least on one or more file-level heuristics. The caching of a storage medium in a caching device is performed by a cache policy engine. The cache policy engine receives file-level information of input/output access of data of the storage medium and caches or evicts the data of the storage medium in the caching device based on the received file-level information. By utilizing information about the files and file operations associated with the disk sectors or logical block addresses of the storage medium, the cache policy engine can make a better decision on the data selection of the storage medium to be cached in or evicted from the caching device in one embodiment of the invention. Higher cache hit rates can be achieved and the performance of the system utilizing the cache policy engine is improved.

Abstract: A method and system to perform caching based at least on one or more file-level heuristics. The caching of a storage medium in a caching device is performed by a cache policy engine. The cache policy engine receives file-level information of input/output access of data of the storage medium and caches or evicts the data of the storage medium in the caching device based on the received file-level information. By utilizing information about the files and file operations associated with the disk sectors or logical block addresses of the storage medium, the cache policy engine can make a better decision on the data selection of the storage medium to be cached in or evicted from the caching device in one embodiment of the invention. Higher cache hit rates can be achieved and the performance of the system utilizing the cache policy engine is improved.

Abstract: A method and apparatus for a multi-ranked memory protocol. In some embodiments an apparatus may include a memory controller (MC), and a plurality of ranked dynamic random access memory (DRAM) devices interfaced with the MC, wherein timing and initiation operations between the MC and the plurality of ranked DRAM devices and between the plurality of ranked DRAM devices is controlled by the MC. In some embodiments, a method may include addressing a request to one of a plurality of ranked DRAM devices, sending the request from a MC interfaced with the plurality of ranked DRAM devices, and propagating the request from the MC through the plurality of ranked DRAM devices to the addressed ranked DRAM device MC, wherein the requests includes data associated therewith.

Abstract: A technique is discussed for representing cores and threads of a multi-core processor as a virtual device with a bridge device with the functionality of a PCI bridge device with an ability to direct configuration accesses to a memory image of the virtual device. The bridge device may be incorporated within an IOH and supports a PCI configuration header with a capability point, to direct configuration accesses to a memory image of the virtual device.