Client Queue Coordination for Shared Resource Power State Transitions

Solution Overview

Problem

In computing devices, uncoordinated accesses to shared resources by clients lead to suboptimal operation and increased electrical power consumption due to frequent transitions between power states, resulting in inefficiencies and delays.

Innovation Solution

Implementing a mechanism where clients buffer job items in a queue until it meets certain conditions, then notify other clients to process these items, coordinating access to shared resources and transitioning them between power states only when necessary, thereby optimizing power usage and processing efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If clients access shared resources in an uncoordinated fashion, then clients can process job items independently, but the shared resource transitions between power states frequently causing increased electrical power consumption and delays

Engineering Contradiction:

Improvejob item processingVSAvoidelectrical power consumption

Core Design Contradiction:

ProductivityVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary actions by buffering job items in a queue at the client before accessing the shared resource. This allows the shared resource to be transitioned to a higher-power state in advance, so when a client needs to access it, the resource is already ready to process job items without causing frequent unnecessary transitions between power states, thereby reducing electrical power consumption while maintaining processing productivity

Inventive Principle:

Principle #10Preliminary action

2Ease of operation

If clients access shared resources in an uncoordinated fashion, then access independence is maintained, but transitions between power states cause increased delays

Engineering Contradiction:

Improveaccess independenceVSAvoidprocessing delays

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system performs preliminary actions by buffering job items in a queue at the client before accessing the shared resource. This allows the shared resource to be transitioned to a higher-power state in advance, so when a client needs to access it, the resource is already ready to process job items without causing frequent unnecessary transitions between power states, thereby reducing electrical power consumption while maintaining processing productivity

Inventive Principle:

Principle #10Preliminary action

3Productivity

If the shared resource is transitioned to a higher-power state frequently, then job items can be processed, but the transitions cost electrical power and load other functional blocks

Engineering Contradiction:

Improvejob item processing capabilityVSAvoidelectrical power consumption during transitions

Core Design Contradiction:

ProductivityVSLoss of energy

Solution Approach 1:

The system performs preliminary actions by buffering job items in a queue at the client before accessing the shared resource. This allows the shared resource to be transitioned to a higher-power state in advance, so when a client needs to access it, the resource is already ready to process job items without causing frequent unnecessary transitions between power states, thereby reducing electrical power consumption while maintaining processing productivity

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system uses feedback mechanisms where clients notify each other about their access needs to the shared resource. This coordination allows the shared resource to be transitioned to a higher-power state only when actually needed, rather than frequently, reducing the energy loss during transitions while maintaining the capability to process job items efficiently

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS10884477B2Coordinating accesses of shared resources by clients in a computing device

Publication Date: 2021.01.05 ADVANCED MICRO DEVICES INC

AI summary

The described embodiments include a computing device with a plurality of clients and a shared resource for processing job items. During operation, a given client of the plurality of clients stores first job items in a queue for the given client. When the queue for the given client meets one or more conditions, the given client notifies one or more other clients that the given client is to process job items using the shared resource. The given client then processes the first job items from the queue using the shared resource. Based on being notified, at least one other client that has second job items to be processed using the shared resource, processes the second job items using the shared resource. The given client can transition the shared resource between power states to enable the processing of job items.