Memristor Crossbar Boolean Evaluation Using Sneak Paths
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing memristor-based crossbar computing systems face challenges in evaluating Boolean formulas due to the sneak-path problem, where current flows through unintended paths, making it difficult to accurately detect memristor resistance and current flow, and often increase fabrication complexity.
Innovation Solution
A memristor-based crossbar design that encodes Boolean formulas using a plurality of memristors, where each memristor is configured as a switch with determined states to create a sneak path allowing current flow from the input nanowire to the output nanowire when the formula is logically true, utilizing nanowires and memristors in a crossbar lattice to evaluate Boolean formulas in negation normal form.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If memristors are organized into crossbar networks for Boolean formula evaluation, then fabrication complexity is reduced and scalability is improved, but current flows through unintended sneak paths making accurate detection difficult
Solution Approach 1:
The patent transforms the harmful sneak path current flows into the basis for computation. By encoding Boolean formulas in the crossbar configuration and applying voltage to input nanowires, the sneak paths that were previously problematic become the computational mechanism itself, where current flow patterns represent logical operations and their presence/absence indicates computation results.
2Ease of operation
If individual memristors are used with non-memristive circuit elements, then Boolean logic operations can be implemented, but device heterogeneity increases fabrication difficulty
Solution Approach 1:
The patent merges the functions of multiple circuit elements into the memristor crossbar structure itself. The memristors serve as both storage elements and logic gates, while the crossbar architecture provides both interconnection and computation. This eliminates the need for separate non-memristive circuit elements, reducing device heterogeneity and simplifying fabrication to a single homogeneous memristor-based platform.
3Ease of operation
If synchronous timing with global clock is used for memristor operations, then sequential logic can be implemented, but design complexity and timing constraints increase significantly
Solution Approach 1:
The patent inverts the conventional approach by eliminating the global clock and synchronous timing requirements. Instead of using timed sequences to implement logic, the system uses the physical presence or absence of sneak path currents to represent logical states directly. This asynchronous approach simplifies design by removing complex timing constraints while maintaining sequential logic capability through the inherent properties of the crossbar configuration.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach efficiently and asynchronously evaluates Boolean formulas with low energy consumption, transforming sneak paths from a problem into a design primitive, enabling accurate computation of Boolean values and simplifying the fabrication process.
Implementation Method 1
a plurality of memristors that serve as switches that in closed positions resist the flow of current
Data Source
AI summary
Memristor-based nano-crossbar computing is a revolutionary computing paradigm that does away with the traditional Von Neumann architectural separation of memory and computation units. The computation of Boolean formulas using memristor circuits has been a subject of several recent investigations. Crossbar computing, in general, has also been a topic of active interest, but sneak paths have posed a hurdle in the design of pervasive general-purpose crossbar computing paradigms. Various embodiments are disclosed which demonstrate that sneak paths in nano-crossbar computing can be exploited to design a Boolean-formula evaluation strategy. Such nano-crossbar designs are also an effective approach for synthesizing high performance customized arithmetic and logic circuits.