Computational Storage Function Grouping for Low-Latency Discovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems lack efficient mechanisms for managing and organizing computational storage functions in storage devices, leading to increased network latencies, power consumption, and difficulty in interoperability across different hardware and software builds.
Innovation Solution
A system and method for grouping computational storage functions using a common naming convention and identifier, enabling seamless interaction and management of these functions across various devices, including NVMe and NVMe-oF enabled storage devices, through application programming interfaces and discovery processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If computational storage functions are managed without a standardized grouping mechanism, then device complexity and difficulty in managing diverse functions increase, but implementing a standardized grouping mechanism requires developing and maintaining naming conventions and classification systems
Solution Approach 1:
The patent applies parameter changes by establishing standardized naming conventions and classification parameters for computational storage functions. Functions are organized using consistent naming patterns (e.g., prefix-suffix structure) and classified by function type, device type, and operational characteristics. This standardization transforms the management of diverse computational functions into a systematic process that improves ease of operation while controlling complexity through structured parameterization.
2Measurement precision
If computational storage functions are discovered and identified through detailed individual queries, then measurement precision and function identification accuracy improve, but network latencies increase due to multiple communication rounds
Solution Approach 1:
The patent implements preliminary action by having the computational storage device proactively publish its function group information to the host system before detailed function queries are needed. The device maintains a published registry of available functions with their standardized names, types, and groupings, allowing the host to quickly identify and select functions without performing multiple sequential discovery queries. This preliminary publication of function metadata significantly reduces network latency while preserving accurate function identification.
3Adaptability or versatility
If computational storage functions are managed without standardized naming conventions, then adaptability to different vendor implementations is improved, but interoperability between different hardware and software builds deteriorates
Solution Approach 1:
The patent applies universality by creating a vendor-agnostic standardized naming convention and function classification system that works across different hardware and software implementations. The standardized names, function types, and grouping mechanisms serve as a universal interface that enables interoperability between diverse computational storage devices while allowing each vendor to implement their specific functions behind this common naming framework. This universal standard ensures reliable communication and function identification across the industry.
4Loss of information
If detailed function information is transmitted through the interface, then completeness of function data improves, but power consumption increases
Solution Approach 1:
The patent applies segmentation by dividing function information into hierarchical levels: function group names, individual function names, and detailed function parameters. The device publishes summarized function group information that provides sufficient detail for most operations without transmitting complete function specifications. Detailed function data is only transmitted when specifically requested and needed, reducing overall power consumption while maintaining information completeness for operational purposes.
Data Source
AI summary
Provided are systems, methods, and apparatuses for managing functions for storage devices. The method can include: determining one or more functions associated with a first device and determining one or more corresponding function types for the functions; grouping the functions based on the function types using a group name; and providing the group name to a second device for use in connection with an associated application, wherein the storage device comprises a computational storage (CS) device.