Database Compute Proxy for PNM Offloading of Access-Intensive Queries
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing database systems like Redis face inefficiencies in time-consuming access-intensive computations due to frequent data transmissions between the processor and memory, leading to prolonged computation times and resource overheads, which current circumvention schemes fail to fundamentally address.
Innovation Solution
Offload access-intensive computations to a Processing Near Memory (PNM) device, utilizing a compute proxy to identify and transfer computations exceeding a data transmission threshold, thereby reducing CPU load and enhancing efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If computations are performed in the traditional CPU-memory architecture, then the database can process various operations, but the data transmission frequency between CPU and memory becomes excessively high, leading to time-consuming computations
Solution Approach 1:
The patent introduces a spatial dimension change by moving computation from the CPU to a PNM device located near the memory. This dimensional shift in computation location reduces the need for frequent data transmission between CPU and memory, thereby reducing computation time while maintaining processing capability
Solution Approach 2:
The patent introduces a PNM device as an intermediary between the CPU and memory. This intermediary performs computations directly on data stored in memory, eliminating the need for data to be transmitted to the CPU first, thus reducing both data transmission frequency and computation time
2Productivity
If access-intensive computations are performed using traditional CPU architecture, then the database can handle data operations, but the frequent data transmission between processor and memory increases resource overhead
Solution Approach 1:
The patent extracts access-intensive computations from the CPU and relocates them to the PNM device. This extraction reduces the computational burden on the CPU and eliminates frequent data transmissions, thereby reducing resource overhead while preserving data operation capability
Solution Approach 2:
The patent changes the spatial dimension of computation by implementing it near the memory rather than at the CPU. This dimensional change reduces data transmission distance and frequency, thereby reducing energy consumption and resource overhead
Data Source
AI summary
A computation management method for managing a database, including: transmitting, by a compute proxy, a computation request to a processing near memory (PNM) device based on determining that a computation to be performed includes a predetermined access-intensive computation in which a data transmission frequency between a processor and a memory is greater than a first predetermined threshold, and the compute proxy is selected to perform the access-intensive computation; and receiving, by the compute proxy, a notification about a computation result generated by the PNM device based on the computation request.