Bit String Accumulation in Memory Array Periphery Using Posit Format
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current computing systems face limitations in precision and accuracy due to finite memory constraints, particularly when performing recursive operations using floating-point formats, which often result in rounding errors and overflow issues.
Innovation Solution
The implementation of a posit format, which allows for higher precision and dynamic range than traditional floating-point formats, enables improved accuracy and reduced memory usage by storing results of recursive operations in peripheral circuitry, such as sense amplifiers, and using a state machine for efficient data retrieval and storage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If floating-point formats are used for recursive operations, then compatibility with existing systems is maintained, but precision and accuracy deteriorate due to rounding errors and overflow issues
Solution Approach 1:
The patent changes the numerical representation parameter from traditional floating-point format to posit format. This parameter change enables higher precision and dynamic range for recursive operations while maintaining system compatibility through standardized implementation interfaces.
Solution Approach 2:
The posit format provides dynamic precision and dynamic range that adapts to the specific requirements of recursive operations. The format can dynamically allocate bits to represent both very small and very large numbers with high precision, unlike fixed-precision floating-point formats.
2Measurement precision
If more memory is allocated for storing intermediate results of recursive operations, then accuracy is improved, but memory consumption increases
Solution Approach 1:
The posit format changes the efficiency parameter of data representation, allowing intermediate results to be stored more compactly. The dynamic range and precision properties of posit enable accurate representation of recursive operation results using fewer memory resources compared to traditional floating-point formats.
3Ease of manufacture
If traditional floating-point formats are used, then implementation simplicity is maintained, but rounding errors and overflow issues occur
Solution Approach 1:
The patent changes the numerical format parameter to posit, which inherently provides better reliability for recursive operations. The posit format's structure with regime, exponent, and fraction fields enables more reliable representation of intermediate results, reducing rounding errors and overflow issues while maintaining implementation feasibility through standardized circuits.
Data Source
AI summary
Systems, apparatuses, and methods related to bit string accumulation in memory array periphery are described. Control circuitry (e.g., a processing device) may be utilized to control performance of operations using bit strings within a memory device. Results of the operations may be accumulated in circuitry peripheral to a memory array of the memory device. For instance, a method for bit string accumulation in memory array periphery can include retrieving a bit string stored in a data structure of a memory array. The bit string can represent a result of performance of an arithmetic operation or a logical operation. The method can further include storing the bit string in a plurality of sense amplifiers located in a periphery of the memory array and using the bit string as an operand in performance of at least a portion of a recursive operation.