Memory Extension Devices for Cross-Host Resource Pooling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud computing systems face inefficiencies in hardware resource allocation due to varying task requirements, leading to suboptimal hardware utilization rates as either processing units or memory spaces often remain idle due to mismatched resource demands.
Innovation Solution
A computing system architecture that allows multiple hosts to be coupled through memory extension devices, enabling each host to access and configure memory spaces across other hosts, thereby improving hardware resource utilization by forming virtual machines that can dynamically allocate idle processing units and memory spaces.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If a task requires a larger memory space, then the memory capacity is improved, but the processing units may have to remain idle due to lack of configurable memory space
Solution Approach 1:
The patent merges memory resources from multiple hosts into a shared memory pool accessible by all hosts through memory extension devices. This allows processing units on one host to utilize memory space from another host, thereby improving both memory capacity availability and processing unit utilization simultaneously.
Solution Approach 2:
The memory extension devices enable memory spaces to serve multiple purposes and multiple hosts simultaneously. A single memory space can be accessed by multiple hosts dynamically, allowing the same physical memory resource to fulfill different computational tasks across the system, improving overall resource utilization.
2Power
If a task requires a larger number of processing units, then the processing power is improved, but the configurable memory space may become insufficient
Solution Approach 1:
The patent combines memory resources from multiple hosts into a unified accessible pool through memory extension devices. This merged memory resource pool can be dynamically allocated to support tasks requiring large numbers of processing units, ensuring sufficient memory capacity is available without being constrained by individual host memory limits.
Solution Approach 2:
Memory extension devices act as intermediaries between hosts and remote memory spaces. These intermediary devices enable processing units to access memory spaces on other hosts without being physically coupled to those memory resources, thereby providing sufficient memory capacity for high-power computational tasks.
3Reliability
If hosts are configured with dedicated memory spaces, then the reliability is improved, but the adaptability of hardware resource allocation deteriorates
Solution Approach 1:
The patent implements dynamic memory allocation where memory spaces are not permanently bound to specific hosts but can be dynamically assigned and reassigned based on task requirements. The memory extension devices enable this dynamic reconfiguration, allowing the system to adapt to varying computational demands while maintaining reliable access through established coupling protocols.
Solution Approach 2:
Memory spaces are designed to serve multiple hosts and multiple tasks universally rather than being dedicated to a single host. This universal accessibility through memory extension devices maintains system reliability through standardized access protocols while dramatically improving adaptability to different computational scenarios.
Data Source
AI summary
The present application discloses a computing system and an associated method. The computing system includes a first host, a second host, a first memory extension device and a second memory extension device. The first host includes a first memory, and the second host includes a second memory. The first host has a plurality of first memory addresses corresponding to a plurality of memory spaces of the first memory, and a plurality of second memory addresses corresponding to a plurality of memory spaces of the second memory. The first memory extension device is coupled to the first host. The second memory extension device is coupled to the second host and the first memory extension device. The first host accesses the plurality of memory spaces of the second memory through the first memory extension device and the second memory extension device.