Current-Mode MAC Circuits for Low-Power Edge AI Conversion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current digital AI & ML solutions are costly and power-hungry, making them unsuitable for edge or sensor applications, and they rely on expensive deep sub-micron manufacturing, which is not necessary for many AI & ML tasks, leading to inefficiencies in power consumption and cost.
Innovation Solution
The development of current-mode data-converters, multipliers, and multiply-accumulate circuits that can interface with digital systems, operate at low power, and are manufactured using mainstream CMOS fabrication, enabling hybrid analog and digital signal processing, asynchronous operations, and memory-free processing to reduce power consumption and cost.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If digital AI & ML solutions are deployed, then ease of interface compatibility and programming flexibility are improved, but power consumption and cost increase significantly
Solution Approach 1:
The patent replaces digital voltage-mode computing with analog current-mode computing. Current-mode operations perform computations directly in the analog domain using current signals, eliminating the need for repeated digital-to-analog conversions and reducing power consumption while maintaining interface compatibility through current-output data converters.
Solution Approach 2:
The patent changes the fundamental operating parameter from voltage to current. By using current-mode logic and current-output data converters, the system achieves lower power consumption because current operations can be performed without the high-voltage swings required by digital logic, while still interfacing with standard digital systems through the data converter interfaces.
2Manufacturing precision
If bleeding edge deep sub-micron manufacturing is used, then manufacturing precision is improved, but cost and power consumption increase
Solution Approach 1:
The patent changes the manufacturing parameter requirement by moving from voltage-mode to current-mode operation. Current-mode circuits are less sensitive to process variations and can achieve acceptable performance with standard CMOS manufacturing processes, eliminating the need for expensive deep sub-micron fabrication while maintaining sufficient precision for AI & ML applications.
Solution Approach 2:
The patent adopts a approach that accepts lower manufacturing precision from standard CMOS processes in exchange for dramatically reduced cost. By designing current-mode circuits that are robust to process variations, the system achieves functional equivalence without requiring expensive precision manufacturing.
3Measurement precision
If high-resolution data converters are used, then measurement precision is improved, but device complexity and power consumption increase
Solution Approach 1:
The patent replaces high-resolution digital processing with lower-resolution analog current-mode processing. By performing computations in the analog domain using current signals, the system achieves sufficient precision for AI & ML applications without requiring high-resolution data converters, thereby reducing complexity and power consumption.
Solution Approach 2:
The patent applies approximate computing principles where full precision is not required. Current-mode operations with lower-resolution data converters provide sufficient accuracy for many AI & ML tasks, allowing the system to use simpler, lower-power converters that perform the necessary computations with acceptable rather than maximum precision.
Data Source
AI summary
Multipliers and Multiply-Accumulate (MAC) circuits are fundamental building blocks in signal processing, including in emerging applications such as machine learning (ML) and artificial intelligence (AI) that predominantly utilize digital-mode multipliers and MACs. Generally, digital multipliers and MACs can operate at high speed with high resolution, and synchronously. As the resolution and speed of digital multipliers and MACs increase, generally the dynamic power consumption and chip size of digital implementations increases substantially that makes them impractical for some ML and AI segments, including in portable, mobile, near edge, or near sensor applications. The multipliers and MACs utilizing the disclosed current mode data-converters are manufacturable in main-stream digital CMOS process, and they can have medium to high resolutions, capable of low power consumptions, having low sensitivity to power supply and temperature variations, as well as operating asynchronously, which makes them suitable for high-volume, low cost, and low power ML and AI applications.