Command Fetch Arbitration with Threshold-Based Burst Scheduling

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing data processing systems face delays and timeouts due to inefficient command fetch operations, particularly when memory systems are engaged in background operations, impacting throughput performance and resource allocation without adequately addressing power consumption and transfer overhead.

Innovation Solution

Implementing a minimum fetch threshold and wait timer mechanism to proactively bundle commands into bursts, ensuring efficient resource utilization by only initiating burst fetches when a minimum number of commands are accumulated, and adjusting wait times based on channel weights and system capabilities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If multi-command fetch is implemented to address slow arbitration turnaround time, then throughput performance is improved, but power consumption and transfer overhead increase

Engineering Contradiction:
Improvethroughput performanceVSAvoidpower consumption
Core Design Contradiction:
ProductivityVSUse of energy by moving object

Solution Approach 1:

The system dynamically adjusts the fetch burst size based on current system conditions, including the number of available commands, channel weights, and resource availability. The arbitration mechanism adapts the fetch parameters in real-time to optimize the balance between throughput and power consumption, rather than using a fixed multi-command fetch approach.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The invention changes key parameters such as the minimum fetch threshold, wait timer duration, and burst size based on system state. By adjusting these parameters dynamically, the system can achieve high throughput when conditions permit while reducing power consumption when commands are scarce or resources are constrained.

Inventive Principle:
Principle #35Parameter changes

2Productivity

If multi-command fetch is implemented to address slow arbitration turnaround time, then throughput performance is improved, but transfer overhead increases

Engineering Contradiction:
Improvethroughput performanceVSAvoidtransfer overhead
Core Design Contradiction:
ProductivityVSLoss of energy

Solution Approach 1:

The arbitration mechanism dynamically determines the optimal burst size based on the number of accumulated commands and system resources. When few commands are available, smaller bursts reduce overhead; when many commands are available, larger bursts improve throughput, creating an adaptive solution that minimizes overhead while maintaining performance.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system accumulates commands in a queue and only initiates burst fetches when a minimum threshold is reached. This preliminary accumulation phase allows the system to batch commands efficiently, reducing the frequency of arbitration operations and minimizing transfer overhead while maintaining high throughput.

Inventive Principle:
Principle #10Preliminary action

3Loss of time

If commands are fetched immediately without bundling, then response time is reduced, but resource allocation efficiency decreases

Engineering Contradiction:
Improveresponse timeVSAvoidresource allocation efficiency
Core Design Contradiction:
Loss of timeVSProductivity

Solution Approach 1:

The system implements a wait timer mechanism that holds commands for a predetermined period or until a minimum fetch threshold is reached. This preliminary waiting period allows commands to be bundled together, improving resource allocation efficiency while the timer ensures that responses are still timely, preventing excessive delays.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The arbitration mechanism uses a minimum fetch threshold that may be exceeded in some cases. By setting a threshold that is sometimes met and sometimes not (depending on command availability), the system achieves a balance between bundling efficiency and response time, implementing partial bundling when appropriate rather than strict all-or-nothing bundling.

Inventive Principle:
Principle #16Partial or excessive action

4Productivity

If bundle fetch is implemented to improve resource allocation, then resource allocation efficiency is improved, but latency increases

Engineering Contradiction:
Improveresource allocation efficiencyVSAvoidlatency
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The system implements a minimum fetch threshold that is not always strictly enforced. When commands accumulate quickly, the threshold is met and bundling occurs; when commands arrive slowly, the threshold may not be met within the wait timer period, and the bundle is issued anyway. This partial enforcement of bundling reduces latency while maintaining resource allocation efficiency in most cases.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The wait timer duration and minimum fetch threshold are dynamically adjusted based on system conditions, including channel weights and resource availability. This dynamic adjustment allows the system to reduce latency when time is critical while maintaining efficient resource allocation when conditions permit longer waiting periods.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP4488840B1System and method for managing arbitration and command fetching
Publication Date: 2026.04.22 SAMSUNG ELECTRONICS CO LTD
  • EP4488840B1 patent drawingFigure 1A
  • EP4488840B1 patent drawingFigure 1B
  • EP4488840B1 patent drawingFigure 2

AI summary

A system and method for managing arbitration and command fetching in a data communication system are provided. The method includes determining that a number of command requests is greater than or equal to a minimum fetch threshold (502) or a number of resources to receive the command requests is greater than or equal to a resource threshold (503), and transmitting the command requests (504) in response to the number of the command requests being greater than or equal to the minimum fetch threshold (502) or the number of resources to receive the command requests being greater than or equal to the resource threshold (503).