Intel Corporation

Shian Tsai, Jr

Tsung-Yuan Charles Tai

Ren Wang

Christian Maciocco

Chih-Fan Hsin

Techniques for collaborative power management for heterogeneous networks are described. An apparatus may include a first node having a managed power system and a power management module to manage power states for the managed power system. The power management module may be operative to communicate power state information with a second node over a communications connection, and manage the power states for the managed power system based on power state information for the second node. Other embodiments are described and claimed.

Techniques for collaborative power management for heterogeneous networks

An embodiment may include network controller circuitry that may be comprised, at least in part, in a host computer. The circuitry may determine, at least in part, based at least in part upon at least one comparison, whether at least one power management action is to be initiated. The at least one comparison may compare, at least in part, at least one pattern with at least one portion of at least one packet received, at least in part, by the host computer. The at least one power management action may include the modification, at least in part, of at least one power management configuration of the host computer. The modification may accommodate, at least in part, at least one packet processing latency policy associated, at least in part, with the at least one pattern. Of course, many alternatives, variations, and modifications are possible without departing from this embodiment.

Method and apparatus for modifying power management configuration of a computer to accommodate a packet processing latency policy associated with a pattern

An embodiment may include circuitry to be comprised in a node. The node may be communicatively coupled to a network and may include a host processor to execute at least one communication protocol-related process. The circuitry may determine, at least in part, whether to buffer, at least in part, at least one packet received from the network based at least in part upon whether a weighted moving average exceeds a first threshold and is less than a second threshold. The average may be determined based at least in part upon one or more time intervals between one or more packet receptions from the network. Many alternatives, variations, and modifications are possible.

Growing community of inventors

Portland, OR, United States of America

Shian Tsai, Jr