Memory Command Prioritization for Lower L2P Mapping Latency

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing memory systems experience latency due to frequent logical-to-physical (L2P) mapping transfers, particularly when multiple virtual machines access a shared memory system, leading to decreased performance.

Innovation Solution

Implementing command prioritization techniques at the host system to group commands with similar parameters or logical address ranges, reducing the need for L2P mapping swaps by ensuring consecutive execution within the same L2P mapping portion.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple virtual machines access a shared memory system concurrently, then memory system versatility and resource sharing are improved, but latency increases due to frequent L2P mapping transfers

Engineering Contradiction:

Improvememory system resource sharingVSAvoidaccess latency

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The host system performs preliminary action by prioritizing commands before they are executed. Commands are analyzed and ordered based on their L2P mapping requirements, ensuring that commands needing the same mapping are grouped together. This preliminary ordering prevents frequent mapping transfers during execution, resolving the latency issue while maintaining multi-VM access capability

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements feedback by monitoring command execution patterns and adjusting command prioritization dynamically. The host system analyzes which commands cause mapping transfers and modifies the prioritization strategy accordingly, creating a closed-loop system that reduces latency while preserving resource sharing efficiency

Inventive Principle:

Principle #23Feedback

2Device complexity

If commands are executed in arrival order (FIFO), then system simplicity is maintained, but performance decreases due to unnecessary L2P mapping swaps

Engineering Contradiction:

Improvecommand queue managementVSAvoidmemory access throughput

Core Design Contradiction:

Device complexityVSProductivity

Solution Approach 1:

The system transitions from static FIFO queue management to dynamic prioritization. Commands are not processed in fixed arrival order but are dynamically reordered based on their L2P mapping characteristics. This dynamic approach groups commands with similar mapping requirements together, reducing mapping swaps and improving throughput without requiring complex queue structures

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The invention changes the parameter of command ordering from time-based (arrival order) to property-based (L2P mapping similarity). By sorting commands based on their mapping characteristics rather than temporal arrival, the system achieves better performance while maintaining relatively simple queue management logic

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20260016991A1Command prioritization techniques for reducing latency in a memory system

Publication Date: 2026.01.15 MICRON TECHNOLOGY INC

AI summary

Methods, systems, and devices for command prioritization techniques for reducing latency in a memory system are described. In some examples, a host system may receive a set of commands from one or more virtual machines to access a common memory system. The host system may store the set of command in a command queue associated with the memory system and arrange the set of command according to order that is based on one or more identified pattern of accessing sequential addresses in the set of commands. The host system may transmit the set of command to the memory system based on the order and the memory system may execute the commands according to the order.