Near-Data Processing Storage for Lower Transfer Overhead
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing storage devices experience overhead and delays in data transfer and processing due to the need for increased computing performance, leading to inefficiencies in data processing speed and power consumption.
Innovation Solution
The storage device is equipped with a core and memory that allows for near-data processing (NDP) by executing processing codes directly, utilizing a memory controller with a sub-memory and main memory to store and execute tasks efficiently, reducing the need for host device processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If data processing is performed by the host device, then computing performance is improved, but overhead and data transfer time increase
Solution Approach 1:
The patent introduces a new spatial dimension for code execution by implementing a code execution engine within the storage device itself, rather than relying solely on the host device. This dimensional shift in where code execution occurs enables parallel processing and eliminates data transfer overhead, as the storage device can execute processing codes locally on stored data without requiring constant host device intervention.
2Productivity
If data processing is performed by the host device, then computing performance is improved, but power consumption increases
Solution Approach 1:
The storage device performs self-service by executing processing codes locally through the code execution engine. This eliminates the need for continuous host device involvement in data processing operations, allowing the storage device to autonomously process data and reduce overall system power consumption by distributing computational tasks to the storage device's own processing resources.
3Ease of operation
If processing codes are executed in the host device, then task processing is simplified, but device complexity increases due to additional storage device processing capabilities
Solution Approach 1:
The patent segments the system into distinct functional components: the host device retains its traditional data access role, while the storage device incorporates a dedicated code execution engine. This segmentation allows each component to specialize in specific tasks, with the storage device handling code execution and the host device handling high-level application logic, thereby managing complexity through functional separation rather than consolidation.
Data Source
AI summary
An operating method of a storage device, including a core and a memory, includes receiving a first processing code configured to enable execution of a first task and storing the first processing code in a first logical unit separately allocated in the memory for near-data processing (NDP), in response to a write command received from a host device, activating the core for executing the first processing code, in response to an activation command received from the host device, and executing the first task by using the core, in response to an execution command received from the host device.