Dynamic Resource Allocation in Mass Memory Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional memory systems have a fixed allocation of resources between host devices and mass memory devices, which can lead to inefficient resource utilization and increased costs due to the need for multiple versions of mass memory devices for different end-products, as well as underutilization or insufficient availability of resources like DRAM.
Innovation Solution
Implementing a dynamic resource allocation system where the host device and mass memory device can agree on the usage of available resources, such as system RAM, CPU cores, or DSP, to perform memory operations, allowing for flexible allocation based on specific needs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If fixed allocation of resources is used between host device and mass memory device, then resource availability is guaranteed, but resource utilization efficiency decreases and manufacturing costs increase
Solution Approach 1:
The patent implements dynamic resource allocation where the mass memory device can request additional processing resources from the host device based on actual operational needs. The system transitions from static, fixed resource allocation to dynamic, demand-based allocation, allowing resources to be shared flexibly between host and mass memory device according to workload requirements.
Solution Approach 2:
The mass memory device is designed with multi-functionality to perform not only storage operations but also processing operations that traditionally required dedicated host resources. By integrating processing capabilities within the mass memory device and enabling resource sharing, the system achieves universal resource utilization across different operational scenarios.
2Adaptability or versatility
If multiple versions of mass memory devices are designed for different end-products, then specific performance requirements are met, but manufacturing costs and device complexity increase
Solution Approach 1:
A single version of the mass memory device is designed with universal functionality to handle multiple performance requirements. The device can dynamically request and utilize additional processing resources from the host based on the specific operational needs of different end-products, eliminating the need for multiple specialized device versions while maintaining performance adaptability.
Solution Approach 2:
The system allows performance parameters to be dynamically adjusted by changing resource allocation parameters rather than designing different hardware configurations. The mass memory device can modify its operational parameters by requesting varying levels of processing resources from the host, enabling adaptation to different performance requirements through parameter changes rather than hardware variations.
3Reliability
If fixed resource allocation is implemented, then resource availability is ensured, but underutilization of resources like DRAM occurs
Solution Approach 1:
The system implements dynamic resource allocation where processing resources such as DRAM are allocated based on actual demand rather than fixed assignments. The mass memory device can request additional processing resources when needed and release them when not required, preventing resource underutilization while maintaining availability through dynamic sharing mechanisms.
Solution Approach 2:
The mass memory device has the capability to self-manage its resource requirements by monitoring its operational needs and requesting appropriate processing resources from the host device. This self-service approach allows the system to optimize resource utilization by allocating DRAM and other processing resources only when and where they are actually needed, rather than through fixed allocation that causes underutilization.
Data Source
AI summary
A memory controller of a mass memory device determining that a memory operation has been initiated which involves the mass memory device, and in response dynamically checks for available processing resources of a host device that is operatively coupled to the mass memory device and thereafter puts at least one of the available processing resources into use for performing the memory operation. In various non-limiting examples: the available processing resources may be a core engine of a multi-core CPU, a DPS or a graphics processor; central processing unit; a digital signal processor; and a graphics processor; and it may also be dynamically checked whether memory resources of the host are available and those can be similarly put into use (e.g., write data to a DRAM of the host, process data in the DRAM with the host DSP, then write the processed data to the mass memory device).