摘要:
A method and system for transmitting packets. Packets may be transmitted when a protocol control block is copied from a host processing system to a network protocol offload engine. Message information that contains packet payload addresses may be provided to the network protocol offload engine to generate a plurality of message contexts in the offload engine. With the message contexts, protocol processing may be performed at the offload engine while leaving the packet payload in the host memory. Thus, packet payloads may be transmitted directly from the host memory to a network communication link during transmission of the packets by the offload engine. Other embodiments are also described.
摘要:
A network controller generates a remote direct memory access segment. In one embodiment, the controller generates an RDMA segment including an RDMA header, markers, and message segment data obtained in a direct memory access operation. Other embodiments are described and claimed.
摘要:
Provided are a method, system, and program for managing memory requests for logic blocks or clients of a device. In one embodiment, busses are separated by the type of data to be carried by the busses. In another aspect, data transfers are decoupled from the memory requests which initiate the data transfers. In another aspect, clients competing for busses are arbitrated and selected memory requests may be provided programmable higher priority than other memory operations of a similar type.
摘要:
Provided are a method, system, and program for managing Input/Output (I/O) requests in a cache memory system. A request is received to data at a memory address in a first memory device, wherein data in the first memory device is cached in a second memory device. A determination is made as to whether to fetch the requested data from the first memory device to cache in the second memory device in response to determining that the requested data is not in the second memory device. The requested data in the first memory device is accessed and the second memory device is bypassed to execute the request in response to determining not to fetch the requested data from the first memory device to cache in the second memory device.
摘要:
Remapping technologies for execution context swap between heterogeneous functional hardware units are described. A computing system includes multiple registers configured to store remote contexts of functional units. A mapping table maps the remote context to the functional units. An execution unit is configured to execute a remapping tool that intercepts an operation to access a remote context of a first functional unit of the plurality of functional units that is taken offline. The remapping tool determines that the first functional unit is remapped to a second functional unit using the mapping table. The operation is performed to access the remote context that is remapped to the second functional unit. The first functional unit and the second functional unit may be heterogeneous functional units.
摘要:
Embodiments of systems, apparatuses, and methods for energy-efficient operation of a device are described. In some embodiments, a cache performance indicator of a cache is monitored, and a set of one or more cache performance parameters based on the cache performance indicator is determined. The cache is dynamically resized to an optimal cache size based on a comparison of the cache performance parameters to their energy-efficient targets to reduce power consumption.
摘要:
In an embodiment, a processor includes a plurality of cores to independently execute instructions, a shared cache coupled to the cores and including a plurality of lines to store data, and a power controller including a low power control logic to calculate a flush latency to flush the shared cache based on a state of the plurality of lines. Other embodiments are described and claimed.
摘要:
In some embodiments, a power up (or power mode) interface is provided whereby a chip's power up signals are encoded into multiple states to provide more functions than the number of signals used to define the states.
摘要:
Systems and methods may provide for identifying a workload cycle for a computing platform, wherein the workload cycle is to include a busy duration and an idle duration. Additionally, platform energy consumption information may be determined for the workload cycle, and a frequency setting may be selected for the busy duration based at least in part on the platform energy consumption information.
摘要:
In one embodiment, a processor includes a plurality of domains each to operate at an independently controllable voltage and frequency, a plurality of linear regulators each to receive a first voltage from an off-chip source and controllable to provide a regulated voltage to at least one of the plurality of domains, and a plurality of selectors each coupled to one of the domains, where each selector is configured to provide a regulated voltage from one of the linear regulators or a bypass voltage to a corresponding domain. Other embodiments are described and claimed.