Circular Queue Configuration for Host Memory Command Processing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current host systems face bottlenecks in processing times due to limited capacity in registers for command storage and concurrent command entry, leading to delays and reduced performance when multiple cores attempt to communicate with memory systems.

Innovation Solution

Implementing multiple circular queues across multiple cores, allowing each core to concurrently enter commands and receive responses, dynamically configuring the number of queues based on parameters such as command size and processing power.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If multiple cores attempt to concurrently enter commands into a limited-capacity register, then command storage capacity is insufficient, but processing time increases due to bottlenecks

Engineering Contradiction:
Improvecommand storage capacityVSAvoidprocessing time
Core Design Contradiction:
Quantity of substanceVSLoss of time

Solution Approach 1:

The patent divides the single register into multiple circular queues, each capable of storing commands independently. This segmentation allows multiple cores to concurrently enter commands into different queues without conflicting for the same storage space, thereby increasing overall command storage capacity and eliminating the bottleneck that caused processing delays

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transitions from a one-dimensional register structure to a multi-dimensional queue system where commands can be organized across multiple queues with different priorities or purposes. This dimensional expansion allows parallel command entry from multiple cores while maintaining organized access patterns

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Productivity

If a single register is used for command storage, then device complexity is low, but productivity decreases due to concurrent access bottlenecks

Engineering Contradiction:
Improvecommand processing throughputVSAvoidqueue configuration complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

By segmenting the register into multiple circular queues, the system enables parallel command processing across different queues, significantly increasing throughput. The segmentation is implemented with clear access rules for each queue, allowing multiple cores to operate concurrently without complex coordination overhead

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements dynamic queue configuration where the number and size of queues can be adjusted based on system conditions and requirements. This dynamic adaptability allows the system to optimize productivity for different workloads while managing complexity through flexible rather than rigid structures

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS20220171572A1Queue configuration for host interface
Publication Date: 2022.06.02 MICRON TECHNOLOGY INC
  • US20220171572A1 patent drawing
  • US20220171572A1 patent drawing
  • US20220171572A1 patent drawing

AI summary

Methods, systems, and devices for queue configuration for host interface are described. An apparatus may include a host system including a first circular queue having a first entry that indicates a first command for a memory system and a location of data associated with the first command. The apparatus may include a controller that may access the first entry of the first circular queue and generate a second command for the memory system based on the data associated with the first command and the first entry. The controller may then transmit the second command to the memory system based on generating the command. The controller may also receive a response from the memory system based on transmitting the command. The controller may remove the first entry from the first circular queue based on receiving the response from the memory system.