Display Pipeline Buffer Sharing for Power Efficiency

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Computer systems face inefficiencies in power usage due to inactive display processing pipelines, which consume resources without contributing to active processing, leading to suboptimal power management and storage capacity utilization.

Innovation Solution

Implementing a method where inactive processing pipelines have their clock signals gated, allowing their buffers to be used for storage, and enabling clock signals based on data thresholds in memory and buffers to optimize power efficiency and storage capacity.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple processing pipelines are maintained in the system, then processing capability and versatility are improved, but power consumption increases due to inactive pipelines continuing to operate

Engineering Contradiction:
Improveprocessing capabilityVSAvoidpower consumption
Core Design Contradiction:
Adaptability or versatilityVSUse of energy by moving object

Solution Approach 1:

The system dynamically adjusts the operational state of processing pipelines based on real-time processing needs. Clock signals to inactive pipelines are gated (disabled) to reduce power consumption, while active pipelines continue to operate normally. This dynamic switching allows the system to maintain multiple processing pipelines for versatility while minimizing power consumption when full capacity is not needed.

Inventive Principle:
Principle #15Dynamics

2Quantity of substance

If buffers in inactive pipelines are repurposed for storage, then storage capacity is improved, but processing speed may be affected due to resource reallocation

Engineering Contradiction:
Improvestorage capacityVSAvoidprocessing speed
Core Design Contradiction:
Quantity of substanceVSSpeed

Solution Approach 1:

Buffers associated with inactive processing pipelines are repurposed to provide additional storage capacity for the actively processing pipeline. This multi-functional use of buffer resources allows the system to increase effective storage without adding dedicated storage hardware. The active pipeline can utilize these repurposed buffers for temporary data storage, frame buffering, or intermediate processing results, thereby increasing storage capacity without compromising the processing speed of active pipelines.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Loss of energy

If clock signals are gated to inactive pipelines, then power efficiency is improved, but system complexity increases due to clock management overhead

Engineering Contradiction:
Improvepower efficiencyVSAvoidclock management overhead
Core Design Contradiction:
Loss of energyVSDevice complexity

Solution Approach 1:

The system implements self-service clock management where the processing pipeline infrastructure automatically handles clock signal gating based on pipeline activity status. The clock gating logic is integrated into the pipeline control mechanism, allowing the system to autonomously determine when to gate or ungat clock signals based on processing demands. This reduces the need for external clock management complexity while achieving significant power savings from inactive pipelines.

Inventive Principle:
Principle #25Self-service

4Quantity of substance

If buffers are used for both active processing and storage, then storage capacity is improved, but buffer management complexity increases

Engineering Contradiction:
Improvestorage capacityVSAvoidbuffer management complexity
Core Design Contradiction:
Quantity of substanceVSDevice complexity

Solution Approach 1:

The buffer allocation mechanism dynamically adjusts based on pipeline activity. When pipelines become inactive, their buffers are automatically made available for storage purposes. When pipelines become active again, their buffers are automatically reallocated for processing. This dynamic buffer management allows the system to increase storage capacity using existing buffer resources without requiring complex manual buffer allocation schemes, as the buffer assignments adapt automatically to changing processing requirements.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS9412147B2Display pipe line buffer sharing
Publication Date: 2016.08.09 APPLE INC
  • US9412147B2 patent drawing
  • US9412147B2 patent drawing
  • US9412147B2 patent drawing

AI summary

An apparatus for processing graphics data may include a plurality of processing pipelines, each pipeline configured to receive and process pixel data. A functional unit may combine the outputs of each processing pipeline. A buffer included in a given processing pipeline may be configured to store data from the functional unit in response to a determination that the given processing pipeline is inactive. The buffer may then send the stored data to a memory.