Memory Controller Target Selection for Computational NVM Workloads

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing computational storage systems face inefficiencies and errors in user-based or application-based specification of computational non-volatile memory (NVM) targets, leading to suboptimal performance and power usage.

Innovation Solution

A target selector within a memory controller automatically selects the most suitable computational storage device by analyzing device capabilities, application requirements, and user preferences, generating execution estimates, and optimizing data movement based on cost, power, and performance criteria.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If user-based or application-based specification of computational NVM targets is used, then flexibility and control are improved, but error-proneness and operational complexity increase

Engineering Contradiction:

ImproveflexibilityVSAvoiderror-proneness

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The patent introduces an automated target selection mechanism that acts as an intermediary between the application and computational NVM targets. This intermediary automatically selects appropriate targets based on execution estimates, eliminating direct user specification while maintaining flexibility through programmable selection criteria.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Adaptability or versatility

If user-based or application-based specification of computational NVM targets is used, then flexibility and control are improved, but operational complexity increases

Engineering Contradiction:

ImproveflexibilityVSAvoidoperational complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system performs self-service by automatically selecting computational NVM targets without requiring user intervention. The automated selection process evaluates execution estimates and makes decisions independently, reducing operational complexity while preserving adaptability through configurable selection parameters.

Inventive Principle:

Principle #25Self-service

3Measurement precision

If automated target selection with execution estimates is implemented, then selection accuracy and performance are improved, but computational overhead increases

Engineering Contradiction:

Improveselection accuracyVSAvoidcomputational overhead

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system applies partial action by computing execution estimates selectively rather than for all possible targets in all cases. The automated selection mechanism evaluates estimates only when needed to resolve target selection decisions, balancing accuracy requirements against computational overhead through conditional estimation.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS12468461B2Automatic selection of computational non-volatile memory targets

Publication Date: 2025.11.11 SK HYNIX NAND PRODUCT SOLUTIONS CORP

AI summary

Systems, apparatuses and methods may provide for memory controller technology that detects an application function, a data specifier associated with the application function, and one or more operating parameters associated with the application function, generates execution estimates for a plurality of computational storage devices based on the application function, the data specifier, the operating parameter(s), and one or more device capabilities associated with the plurality of computational storage devices, and selects a target storage device from the plurality of storage devices based on the execution estimates.