Storage Device Compute Functions for Data Transfer Efficiency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data storage systems face inefficiencies in data transfer operations due to the lack of computational capabilities within storage devices, leading to increased CPU and memory resource utilization, and higher costs, power consumption, and network utilization.
Innovation Solution
Implementing computational transfer methods within storage devices, such as Solid State Drives (SSDs), that allow for the performance of Compute Functions (CFs) on data during read/write operations, leveraging internal processing bandwidth, memory capacity, and hardware automation to reduce data transfers and enhance efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If computational capabilities are added to storage devices, then data transfer efficiency improves and CPU resource utilization decreases, but device complexity increases
Solution Approach 1:
The patent combines computational functions with storage device functions by integrating a processor into the storage device architecture. This allows the storage device to perform data processing operations locally, merging what were previously separate functions (storage and computation) into a single integrated system, thereby improving data transfer efficiency without requiring separate computational hardware
Solution Approach 2:
The storage device is designed with multi-functionality by enabling it to perform both traditional storage operations and computational operations. The processor within the storage device can execute various data processing tasks including filtering, aggregation, and transformation operations, making the storage device a universal component that handles both data management and computation
2Loss of energy
If data processing is performed at the storage device, then network utilization and power consumption decrease, but the storage device requires more processing resources
Solution Approach 1:
The storage device performs data processing operations autonomously without requiring constant host intervention. The integrated processor handles computational tasks locally at the storage device, enabling it to serve itself by processing data in-place rather than requiring data to be transferred to external systems for processing, thereby reducing network utilization and power consumption
Solution Approach 2:
The storage device performs preliminary data processing operations during data transfer operations. By executing filter, aggregate, or transform operations as data is being transferred or stored, the system prepares data in advance for subsequent operations, reducing the need for additional data transfers and associated energy consumption
Data Source
AI summary
Various implementations described herein relate to systems and methods for a storage device (e.g., a Solid State Drive (SSD)) to perform a Compute Function (CF), including receiving a command from a host, the command identifying the CF, and in response to receiving the command, performing the CF on at least one of internal data stored in the storage device or external data transferred from the host to determine the computation result of the CF.