Host Memory Buffer Execution Code Access
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Semiconductor data storage devices face performance degradation due to insufficient internal random accessible memory, which limits their speed and efficiency, especially when relying on nonvolatile memory for execution code storage.
Innovation Solution
The implementation of a data storage device that utilizes a host memory buffer to store and execute execution code, managed by a storage controller and a mapping controller, allowing for real-time download and execution of code from an external host device, thereby enhancing performance and security through encoding and decoding processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If internal random accessible memory capacity is decreased to reduce cost, then manufacturing cost is reduced, but device performance is degraded
Solution Approach 1:
The patent introduces a host memory buffer as an intermediary storage component between the nonvolatile memory device and the host device. The execution code is stored in the host memory buffer instead of requiring large internal RAM in the data storage device. This mediator allows the device to achieve fast code execution speeds without needing expensive internal random accessible memory, thus resolving the contradiction between manufacturing cost and device performance.
2Ease of manufacture
If internal random accessible memory capacity is decreased to reduce cost, then manufacturing cost is reduced, but code access speed is reduced
Solution Approach 1:
The host memory buffer serves as an intermediary that provides fast random access to execution code. By storing the execution code in the host memory buffer (which has faster access characteristics) rather than relying on limited internal RAM or slow nonvolatile memory, the system achieves high code access speed without increasing internal memory capacity, thus maintaining low manufacturing cost while improving access speed.
Solution Approach 2:
The patent shifts the storage location of execution code from the internal memory dimension to the external host memory buffer dimension. This dimensional change allows the system to leverage the host device's memory resources, achieving fast code access without being constrained by the data storage device's internal memory capacity, thereby resolving the speed-cost contradiction.
3Reliability
If execution code is stored in nonvolatile memory, then data persistence is improved, but access speed is reduced
Solution Approach 1:
The host memory buffer acts as an intermediary layer between the nonvolatile memory (which provides persistent storage) and the execution units (which require fast access). The execution code is loaded from nonvolatile memory into the host memory buffer, where it can be accessed rapidly. This mediator resolves the contradiction by allowing the system to maintain data persistence through nonvolatile memory while achieving fast access speeds through the buffer.
Solution Approach 2:
The execution code is preliminarily loaded from nonvolatile memory into the host memory buffer before execution. This preliminary action separates the persistence function (handled by nonvolatile memory) from the access function (handled by the buffer), allowing the system to benefit from both fast access and data persistence without the trade-off that would exist if code were executed directly from nonvolatile memory.
Data Source
AI summary
A data storage device includes a nonvolatile memory device, a storage controller and a mapping controller. The nonvolatile memory device stores an execution code that controls operations of the data storage device. The storage controller uploads and stores the execution code from the nonvolatile memory device to a host memory buffer included in an external host device, and downloads the execution code in realtime from the host memory buffer to execute the execution code that is downloaded from the host memory buffer. The mapping controller manages a mapping table including mapping relations between the execution code and host addresses of the host memory buffer at which the execution code is stored. A speed of accessing the execution code is increased and performance of the data storage device is enhanced by using the host memory buffer as storage of the execution code to control the operation of the data storage device.