Abstract:
PROBLEM TO BE SOLVED: To enable an extend operation by power management of battery-powered mobile devices and systems. SOLUTION: By a personal computer, a transition from a first state to a second state for at least a part of a downstream device can be identified. First and second states may correspond to different levels relating to activity for at least a part of the downstream device. Data corresponding to a service latency can be transmitted to an upstream device in response to the identified transition for one or more upstream devices to manage power based at least in part on the service latency. COPYRIGHT: (C)2010,JPO&INPIT
Abstract:
A novel method and apparatus to cache System Management Mode (SMM) data with other data to improve performance and reduce latency of SMM handler routines. This method and apparatus allows SMM data and non-SMM data to be distinguished in the cache without requiring extra cache bits which can add to the cost of implementation. Since SMM data and non-SMM data can coexist in the cache, there is no need for time consuming cache flush cycles when switching between the two modes. Since SMM data can be cached, performance of SMM routines are improved. This method and apparatus defines the SMRAM address range to be a range of addresses representable by the tag, but not directly corresponding to installed main memory. When accesses are made to SMRAM addresses, they are redirected to an unused portion of main memory. Protection mechanisms may be implemented to limit access to these SMRAM addresses when not in SMM.
Abstract:
A novel method and apparatus to cache System Management Mode (SMM) data with other data to improve performance and reduce latency of SMM handler routines. This method and apparatus allows SMM data and non-SMM data to be distinguished in the cache without requiring extra cache bits which can add to the cost of implementation. Since SMM data and non-SMM data can coexist in the cache, there is no need for time consuming cache flush cycles when switching between the two modes (1150). Since SMM data can be cached, performance of SMM routines are improved. This method and apparatus defines the SMRAM address range to be a range of addresses (1110) representable by the tag, but not directly corresponding to installed main memory. When accesses are made to SMRAM addresses, they are redirected to an unused portion of main memory. Protection mechanisms (1150) may be implemented to limit access to these SMRAM addresses when not in SMM.
Abstract:
A serial interrupt bus protocol is implemented in which any number of peripherals in a computer system may signal any predetermined interrupt signals to the system's interrupt controller (22) without requiring a dedicated pin for each possible interrupt. Each peripheral implemented on the serial interrupt bus incorporates state machine logic for cycling through possible interrupt states. The peripherals are daisy chained beginning and ending with a serial interrupt controller (25) which follows the same state machine logic as the sytem peripherals. When the serial interrupt controller (25) receives an active signal, it determines which interrupt signal to provide to the system's interrupt controller (22) based on the interrupt state of the interrupt controller state machine logic. Peripherals (41, 42) on a secondary serial interrupt bus may be daisy chained with peripherals (30, 31, 32) on a primary system interrupt bus through a system interrupt bridge (40) which also includes state machine logic for following the same state diagram as the system peripherals.
Abstract:
Ausführungsformen eines Systems zum Empfangen von Richtlinien für die Energieverwaltung von einer ersten Vielzahl von Komponenten eines Systems und zu Entwickeln einer Energieverwaltungsstrategie, um eine oder mehrere aus einer zweiten Vielzahl von Komponenten des Systems zu verwalten, basierend wenigstens teilweise auf den empfangenen Richtlinien Tür die Energieverwaltung. Weitere Ausführungsformen sind beschrieben.
Abstract:
A novel method and apparatus to cache System Management Mode (SMM) data with other data to improve performance and reduce latency of SMM handler routines. This method and apparatus allows SMM data and non-SMM data to be distinguished in the cache without requiring extra cache bits which can add to the cost of implementation. Since SMM data and non-SMM data can coexist in the cache, there is no need for time consuming cache flush cycles when switching between the two modes. Since SMM data can be cached, performance of SMM routines are improved. This method and apparatus defines the SMRAM address range to be a range of addresses representable by the tag, but not directly corresponding to installed main memory. When accesses are made to SMRAM addresses, they are redirected to an unused portion of main memory. Protection mechanisms may be implemented to limit access to these SMRAM addresses when not in SMM.
Abstract:
A serial interrupt bus protocol is implemented in which any number of peripherals in a computer system may signal any predetermined interrupt signals to the system's interrupt controller without requiring a dedicated pin for each possible interrupt. Each peripheral implemented on the serial interrupt bus incorporates state machine logic for cycling through possible interrupt states. The peripherals are daisy chained beginning and ending with a serial interrupt controller which follows the same state machine logic as the system peripherals. When the serial interrupt controller receives an active interrupt signal, it determines which interrupt signal to provide to the system's interrupt controller based on the interrupt state of the interrupt controller state machine logic. Peripherals on a secondary serial interrupt bus may be daisy chained with peripherals on a primary system interrupt bus through a system interrupt bridge which also includes state machine logic for following the same state diagram as the system peripherals.
Abstract:
Bei einer offenbarten Ausführungsform kann ein Übergang von einem ersten Zustand in einen zweiten, unterschiedlichen Zustand für zumindest einen Teil eines Downstream-Gerätes identifiziert werden. Die ersten und zweiten Zustände können verschiedene Leveln entsprechen, die die Aktivität für zumindest einen Teil des Downstream-Gerätes betreffen. Daten, die einer Dienstlatenzzeit entsprechen, können in Antwort auf den identifizierten Übergang für ein oder mehr Upstream-Geräte an ein Upstream-Gerät übertragen werden, um Energie zumindest teilweise basierend auf der Dienstlatenzzeit zu regeln. Weitere Ausführungsformen werden ebenfalls offenbart.