Memory-Array Bit String Operations Using Posit Format
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current memory systems face limitations in performing bit string operations efficiently due to the finite memory resources and the inherent limitations of floating-point formats, which can result in reduced accuracy, precision, and increased processing time.
Innovation Solution
The implementation of posit format bit strings within memory arrays, allowing for higher precision, dynamic range, and accuracy through the use of sensing circuitry and control circuitry that converts bit strings between formats, enabling arithmetic and logical operations without transferring data outside the memory array.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If floating-point formats are used in memory systems, then compatibility with existing systems is maintained, but accuracy and precision are reduced
Solution Approach 1:
The patent changes the numerical representation parameter from floating-point format to posit format. This parameter change enables higher accuracy and precision in bit string operations while maintaining system compatibility through the use of format conversion circuitry that translates between different numerical representations.
2Productivity
If bit string operations are performed using conventional memory systems, then existing infrastructure is utilized, but processing time increases
Solution Approach 1:
The patent implements self-service by enabling the memory system to perform bit string operations internally using posit format natively. The sensing circuitry and control circuitry work together to execute arithmetic and logical operations directly within the memory array, eliminating the need to transfer data to external processing units and thereby reducing processing time.
3Use of energy by moving object
If data is transferred between memory array and external circuitry for operations, then existing architecture is maintained, but power consumption increases
Solution Approach 1:
The patent merges the computational functionality with the memory array by integrating posit format operation capabilities directly into the memory structure. The sensing circuitry, which traditionally only reads data, is enhanced to perform arithmetic and logical operations on posit format data directly within the memory array, eliminating data transfer and reducing power consumption.
4Measurement precision
If more memory resources are allocated for operations, then accuracy can be improved, but memory requirements increase
Solution Approach 1:
The patent changes the numerical format parameter to posit, which provides higher precision and accuracy for the same number of bits compared to floating-point formats. This parameter change allows the system to maintain or improve accuracy without increasing memory resource allocation, as the posit format achieves better precision efficiency.
Data Source
AI summary
Systems, apparatuses, and methods related to bit string operations in memory are described. The bit string operations may be performed within a memory array without transferring the bit strings or intermediate results of the operations to circuitry external to the memory array. For instance, sensing circuitry that can include a sense amplifier and a compute component can be coupled to a memory array. A controller can be coupled to the sensing circuitry and can be configured to cause one or more bit strings that are formatted according to a universal number format or a posit format to be transferred from the memory array to the sensing circuitry. The sensing circuitry can perform an arithmetic operation, a logical operation, or both using the one or more bit strings.