Processor-in-Memory Parallel Search for Multi-Stream Data Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current memory devices face inefficiencies in processing and power consumption when performing text or data searches, particularly when searching multiple documents or data streams simultaneously, due to the separation of processing resources from memory devices leading to longer delays and increased power usage.
Innovation Solution
The implementation of a processor-in-memory (PIM) device with a two-dimensional array of memory cells that executes arithmetic and Boolean logical operations in parallel across all columns, allowing for concurrent comparison of data patterns within data streams and storing results in a success indicator row, thereby enabling high-performance searches of large datasets without external processing reliance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If processing resources are external to memory devices, then device complexity is reduced, but processing delays increase and power consumption increases
Solution Approach 1:
The patent combines processing resources directly with memory devices by integrating a processing unit into the memory device structure. This allows data to be processed within the memory device itself rather than being transferred externally, eliminating bus transfer delays and reducing overall processing time while maintaining a unified device architecture.
Solution Approach 2:
The patent introduces a new architectural dimension by embedding processing capabilities within the memory device's internal structure. This creates a hybrid memory-processing unit that operates in parallel, effectively adding a spatial dimension to data processing that eliminates the sequential external processing bottleneck.
2Ease of manufacture
If processing resources are external to memory devices, then ease of manufacture is improved, but power consumption increases
Solution Approach 1:
The patent merges processing and memory functions into a single integrated device, which reduces power consumption by eliminating data transfer between separate components. The processing unit operates directly on data stored in the memory array, avoiding the energy costs of external data movement and processing.
3Device complexity
If data searches are performed using external processing resources, then device complexity is reduced, but productivity decreases
Solution Approach 1:
The patent integrates processing resources directly within the memory device, enabling parallel data search operations across multiple data streams simultaneously. This integration allows the device to perform complex search operations internally without external processing bottlenecks, dramatically improving productivity for tasks like pattern matching and data inquiry.
Solution Approach 2:
The processing unit within the memory device is designed to perform multiple functions including data search, pattern matching, and logical operations. This multi-functional capability allows a single integrated device to handle various data processing tasks that would otherwise require separate external processing resources.
Data Source
AI summary
A method includes comparing, in parallel, a data pattern with data stored into a plurality of columns of memory cells, and in response to detecting the data pattern in the data stored into a particular column of memory cells of the plurality of columns of memory cells, storing in a memory cell of the particular column a value indicative of at least one of an occurrence of the data pattern or a position of the data pattern in the data stored into the particular column.